def display_comparison_plot_mpld3(t, arr, names, line_styles, title, xtitle,
ytitle, ylim, figname):
# Function used to generate interactive d3 plots in html
f, ax = plt.subplots()
lines = []
for i in np.arange(0, len(names)):
l, = ax.plot(t,
arr[:, i],
label=names[i],
lw=3,
ls=line_styles[i],
alpha=0.2)
lines.append(l)
ax.set_xlabel(xtitle)
ax.set_ylabel(ytitle)
ax.set_title(title)
ax = plt.gca()
ax.set_ylim(ylim)
ax.grid()
plugins.connect(f, HighlightLines(lines, names, css))
mpld3.display()
#mpld3.save_html(f, figname + '.html')
return mpld3.fig_to_html(f)
def smithd3(self, x):
import mpld3
import twoport as tp
fig, ax = pl.subplots()
sc = tp.SmithChart(show_cursor=True, labels=True, ax=ax)
sc.plot_s_param(a)
mpld3.display(fig)
def after(self):
if self.draw:
plugins.connect(
self.fig, plugins.InteractiveLegendPlugin(
self.s1, self.labels, ax=self.ax))
mpld3.display()
else:
print meeting.minutes
def plot_ts(*args, **kwargs):
""" Create an interactive JavaScript T-S plot. """
ax = nplt.plot_ts(*args, **kwargs)
pg = InteractiveLegendPlugin(ax.lines,
kwargs.get("labels", [lin.get_label() for lin in ax.lines]),
alpha_unsel=kwargs.get("alpha", 0.2))
plugins.connect(ax.figure, pg)
mpld3.display()
return ax
def plot_ts(*args, **kwargs):
""" Create an interactive JavaScript T-S plot. """
ax = nplt.plot_ts(*args, **kwargs)
pg = InteractiveLegendPlugin(
ax.lines,
kwargs.get("labels", [lin.get_label() for lin in ax.lines]),
alpha_unsel=kwargs.get("alpha", 0.2))
plugins.connect(ax.figure, pg)
mpld3.display()
return ax
def renderGraph(dataSet):
data = dataSet[0]
title = dataSet[1]
ylabel = dataSet[2]
xlabels = dataSet[3]
ind = np.arange(len(data)) # the x locations for the groups
width = 0.35 # the width of the bars
fig, ax = plt.subplots()
#print 'Before figure'
chart = plt.figure()
#print 'After first figure'
rects1 = ax.bar(ind, data, width, color='r')
# add some text for labels, title and axes ticks
ax.set_ylabel(ylabel)
ax.set_title(title)
ax.set_xticks(ind + width / 2)
ax.set_xticklabels(xlabels)
def autolabel(rects):
"""
Attach a text label above each bar displaying its height
"""
for rect in rects:
height = rect.get_height()
ax.text(rect.get_x() + rect.get_width() / 2.,
1.05 * height,
'%d' % int(height),
ha='center',
va='bottom')
autolabel(rects1)
#fig_to_html attempt
#current error: 'Figure' object has no attribute 'fig_to_html'
#needed to download jinja2 for mpld3 to work
graphOutput = plt.figure(
) #initialize variable as current graph to be later passed on to HTML code
graphHTML = fig_to_html(graphOutput) #convert current graph to HTML code
#print graphHTML
#plt.show()
plt.close(graphOutput) #close the current graph
mpld3.display(chart)
return graphHTML
def plot_by_mpld3(dataframe,figsize=(12,6),marker='o',grid=True,
alpha_ax=0.3,alpha_plot=0.4,alpha_unsel=0.3,alpha_over=1.5,
title=None,xlabel=None,ylabel=None,mode="display",file=None):
## DataFrame 데이터를 이용하여 웹용 D3 chart 스크립트 생성
# plot line + confidence interval
fig, ax = plt.subplots(figsize=figsize)
ax.grid(grid, alpha=alpha_ax)
for key, val in dataframe.iteritems():
l, = ax.plot(val.index, val.values, label=key, marker=marker)
ax.plot(val.index,val.values, color=l.get_color(), alpha=alpha_plot)
# define interactive legend
handles, labels = ax.get_legend_handles_labels() # return lines and labels
interactive_legend = plugins.InteractiveLegendPlugin(handles,labels,
alpha_unsel=alpha_unsel,
alpha_over=alpha_over,
start_visible=True)
plugins.connect(fig, interactive_legend)
if xlabel:
ax.set_xlabel(xlabel)
if ylabel:
ax.set_ylabel(ylabel)
if title:
ax.set_title(title, size=len(title)+5)
## mode
if mode == 'html': # return html script
return mpld3.fig_to_html(fig)
elif mode == 'save' and file: # save file
mpld3.save_html(fig,file)
else: # display chart
#mpld3.enable_notebook()
return mpld3.display()
def _scatter_plot(X, y, point_labels, scatter_params, css):
X = pd.DataFrame(X, columns=['x', 'y'])
fig, ax = plt.subplots(figsize=(8, 8))
if 'figsize' in scatter_params:
fig, ax = plt.subplots(figsize=scatter_params['figsize'])
del scatter_params['figsize']
colors, classes = None, None
if y.dtype == 'object':
colors, classes = y.factorize()
else:
colors = y
scatter = ax.scatter(x=X['x'], y=X['y'], c=colors, **scatter_params)
if point_labels is not None and len(point_labels) > 0:
tooltip = mpld3.plugins.PointHTMLTooltip(scatter,
labels=point_labels,
css=css)
mpld3.plugins.connect(fig, tooltip)
else:
mpld3.plugins.connect(fig)
return mpld3.display()
def zoomable_walk(adn):
print("longueur de la séquence d'entrée", len(adn))
X, Y = path_x_y(adn)
pyplot.plot(X, Y)
# au lieu d'afficher le dessin avec pyplot.show()
# on retourne un objet HTML qui est rendu par le notebook
return mpld3.display()
def plot_mle_graph(function,
mle_params,
x_start=eps, x_end=1 - eps,
y_start=eps, y_end=1 - eps, resolution=100,
x_label="x", y_label="y",
show_constraint=False,
show_optimum=False):
x = np.linspace(x_start, x_end, resolution)
y = np.linspace(y_start, y_end, resolution)
xx, yy = np.meshgrid(x, y)
np_func = np.vectorize(lambda x, y: function(x, y))
z = np_func(xx, yy)
optimal_loss = function(*mle_params)
levels_before = np.arange(optimal_loss - 3.0, optimal_loss, 0.25)
levels_after = np.arange(optimal_loss, min(optimal_loss + 2.0, -0.1), 0.25)
fig = plt.figure()
contour = plt.contour(x, y, z, levels=np.concatenate([levels_before, levels_after]))
plt.xlabel(x_label)
plt.ylabel(y_label)
if show_constraint:
plt.plot(x, 1 - x)
if show_optimum:
plt.plot(mle_params[0], mle_params[1], 'ro')
plt.clabel(contour)
return mpld3.display(fig)
def plot_mle_graph(function,
mle_params,
x_start=eps,
x_end=1 - eps,
y_start=eps,
y_end=1 - eps,
resolution=100,
x_label="x",
y_label="y",
show_constraint=False,
show_optimum=False):
x = np.linspace(x_start, x_end, resolution)
y = np.linspace(y_start, y_end, resolution)
xx, yy = np.meshgrid(x, y)
np_func = np.vectorize(lambda x, y: function(x, y))
z = np_func(xx, yy)
optimal_loss = function(*mle_params)
levels_before = np.arange(optimal_loss - 3.0, optimal_loss, 0.25)
levels_after = np.arange(optimal_loss, min(optimal_loss + 2.0, -0.1), 0.25)
fig = plt.figure()
contour = plt.contour(x,
y,
z,
levels=np.concatenate([levels_before, levels_after]))
plt.xlabel(x_label)
plt.ylabel(y_label)
if show_constraint:
plt.plot(x, 1 - x)
if show_optimum:
plt.plot(mle_params[0], mle_params[1], 'ro')
plt.clabel(contour)
return mpld3.display(fig)
def renderGraph(dataSet):
"""
The renderGraph function converts data into a bar graph object. It handles the measuring, drawing, and defining of the various aspects of the graph. From this point, it converts the graph code from Python to HTML and returns this value. This HTML code is then transferred to the website for the viewer.
"""
data = dataSet[0]
title = dataSet[1]
ylabel = dataSet[2]
xlabels = dataSet[3]
dsize=len(data)
ind = np.arange(dsize) # the x locations for the groups
width = 0.35 # the width of the bars
#print 'Before figure'
chart = plt.figure(1)
chart.set_figwidth((11))
#print 'After first figure'
ax=plt.subplot(autoscale_on=True)
rects1 = ax.bar(ind, data, width, color='r')
# add some text for labels, title and axes ticks
ax.set_ylabel(ylabel)
ax.set_title(title)
ax.set_xticks(ind + width / 2)
ax.set_xticklabels(xlabels)
def autolabel(rects):
"""
Function attaches a text label above each bar displaying its height. This function provides the reader easy context on each value in the finished graph so that an understanding of the data can be made faster.
"""
for rect in rects:
height = rect.get_height()
ax.text(rect.get_x() + rect.get_width()/2., 1.02*height,
'%d' % int(height),
ha='center', va='bottom')
autolabel(rects1)
#fig_to_html attempt
#current error: 'Figure' object has no attribute 'fig_to_html'
#needed to download jinja2 for mpld3 to work
chart.tight_layout()
graphOutput = plt.figure() #initialize variable as current graph to be later passed on to HTML code
graphHTML = fig_to_html(chart) #convert current graph to HTML code
#plt.show()
plt.close(graphOutput) #close the current graph
mpld3.display(chart)
return graphHTML
def make_mpld3_mds_plot(xs,ys,data_pd=gdata_pd):
cluster_colors = {'conservative': '#1b9e77', 'liberal': '#d95f02'}
# Define new dataframe with MDS coordinates, some things from original DF.
plot_df = pd.DataFrame(dict(x=xs, y=ys, label=data_pd.loc[:,'leaning'], source=data_pd.loc[:,'source']))
groups = plot_df.groupby('label')
#css formatting
css = """
text.mpld3-text, div.mpld3-tooltip {
font-family:Arial, Helvetica, sans-serif;
}
g.mpld3-xaxis, g.mpld3-yaxis {
display: none; }
svg.mpld3-figure {
margin-left: 0px;}
"""
# margin as -200px
fig, ax = plt.subplots(figsize=(14,6))
for name, group in groups:
points = ax.plot(group.x, group.y, marker='o', linestyle='', ms=18, label=name, mec='none', color=cluster_colors[name])
ax.set_aspect('auto')
labels = [i for i in group.source]
# MPLD3 Setup
tooltip = mpld3.plugins.PointHTMLTooltip(points[0], labels,voffset=10, hoffset=10, css=css)
mpld3.plugins.connect(fig, tooltip, TopToolbar())
# No axes, qualitative plot
ax.axes.get_xaxis().set_ticks([])
ax.axes.get_yaxis().set_ticks([])
ax.axes.get_xaxis().set_visible(False)
ax.axes.get_yaxis().set_visible(False)
ax.legend(numpoints=1)
mpld3.display()
# export html
html = mpld3.fig_to_html(fig)
return
def plot_1D(loss, theta1, theta2, N=100, eps=0.01, loss2=None, ylim=None):
x = np.linspace(eps, 1.0 - eps, N)
fig = plt.figure()
if ylim is not None:
plt.ylim(ylim)
create_1D_plot(x, loss, theta1, theta2)
if loss2 is not None:
create_1D_plot(x, loss2, theta1, theta2)
return mpld3.display(fig)
def display_comparison_plot_mpld3(t, arr, names, line_styles, title, xtitle, ytitle, ylim, figname):
# Function used to generate interactive d3 plots in html
f, ax = plt.subplots()
lines = []
for i in np.arange(0, len(names)):
l, = ax.plot(t, arr[:, i], label=names[i], lw=3, ls=line_styles[i], alpha=0.2)
lines.append(l)
ax.set_xlabel(xtitle)
ax.set_ylabel(ytitle)
ax.set_title(title)
ax = plt.gca()
ax.set_ylim(ylim)
ax.grid()
plugins.connect(f, HighlightLines(lines, names, css))
mpld3.display()
#mpld3.save_html(f, figname + '.html')
return mpld3.fig_to_html(f)
def dataVisualDynamtic(xs,ys,clusters,titles):
# 用 MDS 后的结果加上聚类编号和绘色创建 DataFrame
df = pd.DataFrame(dict(x=xs, y=ys, label=clusters, title=titles))
# 聚类归类
groups = df.groupby('label')
# 自定义 css 对字体格式化以及移除坐标轴标签
css = """
text.mpld3-text, div.mpld3-tooltip { font-family:Arial, Helvetica, sans-serif; }
g.mpld3-xaxis, g.mpld3-yaxis { display: none; }
svg.mpld3-figure { margin-left: -200px;}
"""
# 绘图
fig, ax = plt.subplots(figsize=(14,6)) # 设置大小
ax.margins(0.03) # 可选项，只添加 5% 的填充（padding）来自动缩放
# 对聚类进行迭代并分布在绘图,用到了 cluster_name 和 cluster_color 字典的“name”项，这样会返回相应的 color 和 label
for name, group in groups:
points = ax.plot(group.x, group.y, marker='o', linestyle='', ms=18,label=cluster_names[name], mec='none', color=cluster_colors[name])
ax.set_aspect('auto')
labels = [i for i in group.title]
# 用点来设置气泡消息，标签以及已经定义的“css”
tooltip = mpld3.plugins.PointHTMLTooltip(points[0], labels, voffset=10, hoffset=10, css=css)
# 将气泡消息与散点图联系起来
mpld3.plugins.connect(fig, tooltip, TopToolbar())
# 隐藏刻度线（tick marks）
ax.axes.get_xaxis().set_ticks([])
ax.axes.get_yaxis().set_ticks([])
# 隐藏坐标轴
ax.axes.get_xaxis().set_visible(False)
ax.axes.get_yaxis().set_visible(False)
ax.legend(numpoints=1) # 图例中每项只显示一个点
mpld3.display()
def plot_2D_function(function, x_start=eps, x_end=1 - eps,
y_start=eps, y_end=1 - eps, resolution=100,
x_label="x", y_label="y"):
x = np.linspace(x_start, x_end, resolution)
y = np.linspace(y_start, y_end, resolution)
xx, yy = np.meshgrid(x, y)
np_func = np.vectorize(lambda x, y: function(x, y))
z = np_func(xx, yy)
fig = plt.figure()
contour = plt.contour(x, y, z)
plt.xlabel(x_label)
plt.ylabel(y_label)
plt.clabel(contour)
return mpld3.display(fig)
def plot_tree_mpld3(nodes: List[str],
edgelist: List[Tuple[str]],
svgs: List[Any],
extra_string: Optional[List] = None,
figsize: Optional[Tuple[int, int]] = None,
layout: str = 'rt',
figure_savefile: Optional[str] = None):
G = Graph()
G.add_vertices(nodes)
G.add_edges(edgelist)
if extra_string:
lookup_str = "encoding='iso-8859-1'?>\n" # in the svg
style = 'style="background-color:#ffffff"'
for i, (exs, svg) in enumerate(zip(extra_string, svgs)):
str_pos = svg.find(lookup_str) + len(lookup_str)
_insert = ''.join(
[f'<div {style}>{x}</div>' for x in exs.split('\n')])
svgs[i] = svg[:str_pos] + _insert + svg[str_pos:]
x_edges, y_edges, x_nodes, y_nodes = compute_layout(G, layout)
fig, ax = plt.subplots(figsize=figsize)
for x, y in zip(x_edges, y_edges):
ax.plot(x, y, c='gray', linestyle='--')
points = ax.scatter(x_nodes, y_nodes, s=150, c='gray')
tooltip = plugins.PointHTMLTooltip(points, svgs)
plugins.connect(fig, tooltip)
if figure_savefile is not None:
with open(figure_savefile, 'w') as f:
save_html(fig, f)
display(fig)
def plot_bar_graph(values, labels, rotation=0, align='center', use_mpld3=False):
"""
Plots a bar graph.
Args:
use_mpld3: should we use mpld3 to render the graph.
rotation: by which angle should the labels be rotated.
align: how to align the labels
values: bar values.
labels: bar labels
Returns: None
"""
fig = plt.figure()
plt.xticks([float(x) for x in range(0, len(values))], labels, rotation=rotation)
plt.bar(range(0, len(values)), values, align=align)
if use_mpld3:
return mpld3.display(fig)
def visualizeAmAll(self):
df = pd.read_csv('Data/amazonAll' + self.twitterData)
tweets = df.iloc[:, [
False, True, False, False, False, False, False, False, False
]].to_numpy()
df = pd.read_csv('Data/amazonAll' + self.twitterPreds)
predictions = df.iloc[:,
[False, True, True, True, True, True]].to_numpy(
)
tweets = np.array(
[elem for singleList in tweets for elem in singleList])
singlePred, confidence = interpretPreds(predictions)
#print(singlePred)
fig = plt.Figure()
barChartPreds(singlePred)
return mpld3.display(fig)
def plot_ObsConfused(self,classes,preds,globalLim=10,globalNbCols=2,
lim=10,limByPlots=100,elemsByRows=10,nbCols=2,mods=[],title=None,modelsNames=None,filename=None,titleFontsize=19,**plotConfMat_kwargs):
# from ..helpers import plotDigits
obj=self.obj
modsN=obj.papa._models.namesModels
models=obj.resultats
if len(mods)>0:
mods_ = [i if isStr(i) else modsN[i] for i in mods]
models= [obj.resultats[i] for i in mods_]
modelsNames_=[i for i in mods_]
models=dict(zip(modelsNames_,models)) if modelsNames is None else dict(zip(modelsNames,models))
# namesY= namesEscape(namesY) if namesY is not None else namesY
confMatM=[v.viz.plot_ObsConfused(classes,preds,lim=lim,limByPlots=limByPlots,
elemsByRows=elemsByRows,returnOK=True,nbCols=nbCols,show=False,**plotConfMat_kwargs) for v in models.values()]
title = "ObsConfused CV {}".format(obj.ID) if title is None else title
filename="obj_confused_cv_{}.png".format(obj.ID) if filename is None else filename
# print(confMatM)
img=IMG_GRID.grid(confMatM,nbCols=globalNbCols,toImg=True,title=title,titleFontsize=titleFontsize)
# img.show(figsize=img.figsize,show=True);
# print(img.data)
fig=img.show(returnFig=True,show=False,figsize=img.figsize)
from IPython.display import display_html, HTML
import mpld3
# mpld3.enable_notebook()
display_html(HTML("""
<style>
g.mpld3-xaxis, g.mpld3-yaxis {
display: none;
}
</style>
"""))
# # print(img)
# # print(img.filename)
# # print(img.data)
display_html(HTML("""
<span style='width:20px;height:20px;position: absolute;' title="Save image as png">
<a href="data:image/png;base64,{{imgData}}" download="{{filename}}"><img width="20px" src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABoAAAAaCAYAAACpSkzOAAAABmJLR0QA/wD/AP+gvaeTAAAAs0lEQVRIie2WPQ6DMAxGXzJwqIrerN3pORi7cqWwtjegQymyUlMZCIlU8UleIvt7cv4BKuAG9MCQIJ7ABfBEapTkU5xkVC087mMTk4ICskqrkWOdhGntpwJ9OvNuxtgtAMU1mt81F+iRC/S9BfdScVBtrHciAM6/Epds59UqPnW7KMUdp0nee0O8RtbzY9Xk/X9rdIAOUBlQn4ETPNCKAevzYJF8Mlp4f4ca9G/X1gijd/UCDStihJWAousAAAAASUVORK5CYII="></a></span>
""".replace("{{imgData}}",str(img.data)[2:-1]).replace("{{filename}}",filename)))
display_html(mpld3.display(fig))
plt.close()
def plot_2D_function(function,
x_start=eps,
x_end=1 - eps,
y_start=eps,
y_end=1 - eps,
resolution=100,
x_label="x",
y_label="y"):
x = np.linspace(x_start, x_end, resolution)
y = np.linspace(y_start, y_end, resolution)
xx, yy = np.meshgrid(x, y)
np_func = np.vectorize(lambda x, y: function(x, y))
z = np_func(xx, yy)
fig = plt.figure()
contour = plt.contour(x, y, z)
plt.xlabel(x_label)
plt.ylabel(y_label)
plt.clabel(contour)
return mpld3.display(fig)
def scatterz(x, y, data, labels, xscale='linear', yscale='linear', n=250):
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#FFFFFF'), figsize=(10, 10))
fig.set_size_inches(8, 8)
data = data.head(n)
scatter = ax.scatter(data[x], data[y], s=25, alpha=0.5)
ax.grid(color='white', linestyle='solid')
if yscale == 'linear':
yl = data[y].min()
yh = data[y].max()
yx = (yh - yl) * 0.035
yl = yl - yx
yh = yh + yx
plt.ylim((yl, yh))
elif yscale == 'log':
plt.yscale("log")
if xscale == 'linear':
xl = data[x].min()
xh = data[x].max()
xx = (xh - xl) * 0.035
xl = xl - xx
xh = xh + xx
plt.xlim((xl, xh))
elif xscale == 'log':
plt.xscale("log")
plt.xlabel(x, fontsize=18, labelpad=15, color="gray")
plt.ylabel(y, fontsize=18, labelpad=15, color="gray")
labels = [' {0}'.format(i + str(' ')) for i in data[labels].astype(str)]
tooltip = mpld3.plugins.PointLabelTooltip(scatter, labels=labels)
mpld3.plugins.connect(fig, tooltip)
return mpld3.display()
def display(self,
legend=True,
update=True,
use_mpld3=True,
hide_volume_labels=False,
**kw):
"""Generate the figure and return an object for display
This function is for viewing figures in a Jupyter notebook
Arguments:
legend - boolean for displaying a legend
Default: True
update - boolean for reapplying spine, tick, title and
axis limits to the graph
Default: True
use_mpld3 - boolean for using mpld3 to produce interactive html
Default: True
hide_volume_labels - boolean for hiding x axis volume labels
Default: False
**kw - additional keyword arguments are passed to mpld3.display
"""
if legend == True:
self.add_legend()
elif legend == 'custom':
pass
else:
self.remove_legend()
if update:
self.set_spines_and_ticks()
self.set_title_and_labels(hide_volume_labels=hide_volume_labels)
self.set_limits()
if use_mpld3:
return mpld3.display(self.fig, **kw)
else:
return self.fig
def plot_bar_graph(values,
labels,
rotation=0,
align='center',
use_mpld3=False):
"""
Plots a bar graph.
Args:
use_mpld3: should we use mpld3 to render the graph.
rotation: by which angle should the labels be rotated.
align: how to align the labels
values: bar values.
labels: bar labels
Returns: None
"""
fig = plt.figure()
plt.xticks([float(x) for x in range(0, len(values))],
labels,
rotation=rotation)
plt.bar(range(0, len(values)), values, align=align)
if use_mpld3:
return mpld3.display(fig)
def scatterplot(self, year):
assert year in self.years
df = self.data[year]
reserve = df.loc[:, ["Coal(tCO2)", "Oil(tCO2)", "Gas(tCO2)"]].sum(axis=1)
emv = df.loc[:, ["EndingMarketValue"]]
N = len(df.index)
fig, ax = plt.subplots()
sp = ax.scatter(emv, reserve)
ax.set_xlabel("Equity Invested (USD)")
ax.set_ylabel("Carbon Reserves (tCO2)")
ax.set_title(f"Invested Fossil Fuel Companies in {year}")
ax.get_xaxis().set_major_formatter(
matplotlib.ticker.FuncFormatter(lambda x, p: format(int(x), ',')))
ax.get_yaxis().set_major_formatter(
matplotlib.ticker.FuncFormatter(lambda x, p: format(int(x), ',')))
labels = df.loc[:, "Company(Company)"].values.tolist()
tooltip = mpld3.plugins.PointLabelTooltip(sp, labels=labels)
mpld3.plugins.connect(fig, tooltip)
return mpld3.display()
hoffset=10,
css=css)
#connect tooltip to fig
mpld3.plugins.connect(fig, tooltip, TopToolbar())
#set tick marks as blank
ax.axes.get_xaxis().set_ticks([])
ax.axes.get_yaxis().set_ticks([])
#set axis as blank
ax.axes.get_xaxis().set_visible(False)
ax.axes.get_yaxis().set_visible(False)
ax.legend(numpoints=0.5) #show legend with only one dot
mpld3.display() #show the plot
#uncomment the below to export to html
#html = mpld3.fig_to_html(fig)
#print(html)
# In[193]:
# Plot silhouette distribution
X = tfidf_matrix
range_n_clusters = [12]
for n_clusters in range_n_clusters:
# Create a subplot with 1 row and 2 columns
fig, (ax1, ax2) = plt.subplots(1, 2)
fig.set_size_inches(18, 7)
def plotter(df,
title=False,
kind='line',
x_label=None,
y_label=None,
style='ggplot',
figsize=(8, 4),
save=False,
legend_pos='best',
reverse_legend='guess',
num_to_plot=7,
tex='try',
colours='default',
cumulative=False,
pie_legend=True,
partial_pie=False,
show_totals=False,
transparent=False,
output_format='png',
interactive=False,
black_and_white=False,
show_p_val=False,
indices=False,
transpose=False,
rot=False,
**kwargs):
"""Visualise corpus interrogations.
:param title: A title for the plot
:type title: str
:param df: Data to be plotted
:type df: Pandas DataFrame
:param x_label: A label for the x axis
:type x_label: str
:param y_label: A label for the y axis
:type y_label: str
:param kind: The kind of chart to make
:type kind: str ('line'/'bar'/'barh'/'pie'/'area')
:param style: Visual theme of plot
:type style: str ('ggplot'/'bmh'/'fivethirtyeight'/'seaborn-talk'/etc)
:param figsize: Size of plot
:type figsize: tuple (int, int)
:param save: If bool, save with *title* as name; if str, use str as name
:type save: bool/str
:param legend_pos: Where to place legend
:type legend_pos: str ('upper right'/'outside right'/etc)
:param reverse_legend: Reverse the order of the legend
:type reverse_legend: bool
:param num_to_plot: How many columns to plot
:type num_to_plot: int/'all'
:param tex: Use TeX to draw plot text
:type tex: bool
:param colours: Colourmap for lines/bars/slices
:type colours: str
:param cumulative: Plot values cumulatively
:type cumulative: bool
:param pie_legend: Show a legend for pie chart
:type pie_legend: bool
:param partial_pie: Allow plotting of pie slices only
:type partial_pie: bool
:param show_totals: Print sums in plot where possible
:type show_totals: str -- 'legend'/'plot'/'both'
:param transparent: Transparent .png background
:type transparent: bool
:param output_format: File format for saved image
:type output_format: str -- 'png'/'pdf'
:param black_and_white: Create black and white line styles
:type black_and_white: bool
:param show_p_val: Attempt to print p values in legend if contained in df
:type show_p_val: bool
:param indices: To use when plotting "distance from root"
:type indices: bool
:param stacked: When making bar chart, stack bars on top of one another
:type stacked: str
:param filled: For area and bar charts, make every column sum to 100
:type filled: str
:param legend: Show a legend
:type legend: bool
:param rot: Rotate x axis ticks by *rot* degrees
:type rot: int
:param subplots: Plot each column separately
:type subplots: bool
:param layout: Grid shape to use when *subplots* is True
:type layout: tuple -- (int, int)
:param interactive: Experimental interactive options
:type interactive: list -- [1, 2, 3]
:returns: matplotlib figure
"""
import corpkit
import os
try:
from IPython.utils.shimmodule import ShimWarning
import warnings
warnings.simplefilter('ignore', ShimWarning)
except:
pass
kwargs['rot'] = rot
xtickspan = kwargs.pop('xtickspan', False)
import matplotlib as mpl
from matplotlib import rc
# prefer seaborn plotting
try:
import seaborn as sns
except ImportError:
pass
except AttributeError:
pass
if interactive:
import matplotlib.pyplot as plt, mpld3
else:
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
import pandas
from pandas import DataFrame, Series
from time import localtime, strftime
from process import checkstack
if interactive:
import mpld3
import collections
from mpld3 import plugins, utils
from plugins import InteractiveLegendPlugin, HighlightLines
have_mpldc = False
try:
from mpldatacursor import datacursor, HighlightingDataCursor
have_mpldc = True
except ImportError:
pass
# check what environment we're in
tk = checkstack('tkinter')
running_python_tex = checkstack('pythontex')
running_spider = checkstack('spyder')
if not title:
title = ''
def truncate_colormap(cmap, minval=0.0, maxval=1.0, n=100):
"""remove extreme values from colourmap --- no pure white"""
import matplotlib.colors as colors
import numpy as np
new_cmap = colors.LinearSegmentedColormap.from_list(
'trunc({n},{a:.2f},{b:.2f})'.format(n=cmap.name,
a=minval,
b=maxval),
cmap(np.linspace(minval, maxval, n)))
return new_cmap
def get_savename(imagefolder, save=False, title=False, ext='png'):
"""Come up with the savename for the image."""
import os
from corpkit.process import urlify
# name as
if not ext.startswith('.'):
ext = '.' + ext
if isinstance(save, STRINGTYPE):
savename = os.path.join(imagefolder, (urlify(save) + ext))
#this 'else' is redundant now that title is obligatory
else:
if title:
filename = urlify(title) + ext
savename = os.path.join(imagefolder, filename)
# remove duplicated ext
if savename.endswith('%s%s' % (ext, ext)):
savename = savename.replace('%s%s' % (ext, ext), ext, 1)
return savename
def rename_data_with_total(dataframe,
was_series=False,
using_tex=False,
absolutes=True):
"""adds totals (abs, rel, keyness) to entry name strings"""
if was_series:
where_the_words_are = dataframe.index
else:
where_the_words_are = dataframe.columns
the_labs = []
for w in list(where_the_words_are):
if not absolutes:
if was_series:
perc = dataframe.T[w][0]
else:
the_labs.append(w)
continue
if using_tex:
the_labs.append('%s (%.2f\%%)' % (w, perc))
else:
the_labs.append('%s (%.2f %%)' % (w, perc))
else:
if was_series:
score = dataframe.T[w].sum()
else:
score = dataframe[w].sum()
if using_tex:
the_labs.append('%s (n=%d)' % (w, score))
else:
the_labs.append('%s (n=%d)' % (w, score))
if not was_series:
dataframe.columns = the_labs
else:
vals = list(dataframe[list(dataframe.columns)[0]].values)
dataframe = pandas.DataFrame(vals, index=the_labs)
dataframe.columns = ['Total']
return dataframe
def auto_explode(dataframe, tinput, was_series=False, num_to_plot=7):
"""give me a list of strings and i'll output explode option"""
output = [0 for s in range(num_to_plot)]
if was_series:
l = list(dataframe.index)
else:
l = list(dataframe.columns)
if isinstance(tinput, (STRINGTYPE, int)):
tinput = [tinput]
if isinstance(tinput, list):
for i in tinput:
if isinstance(i, STRINGTYPE):
index = l.index(i)
else:
index = i
output[index] = 0.1
return output
# get a few options from kwargs
sbplt = kwargs.get('subplots', False)
show_grid = kwargs.pop('grid', True)
the_rotation = kwargs.get('rot', False)
dragmode = kwargs.pop('draggable', False)
leg_frame = kwargs.pop('legend_frame', True)
leg_alpha = kwargs.pop('legend_alpha', 0.8)
# auto set num to plot based on layout
lo = kwargs.get('layout', None)
if lo:
num_to_plot = lo[0] * lo[1]
# todo: get this dynamically instead.
styles = [
'dark_background', 'bmh', 'grayscale', 'ggplot', 'fivethirtyeight',
'matplotlib', False, 'mpl-white'
]
#if style not in styles:
#raise ValueError('Style %s not found. Use %s' % (str(style), ', '.join(styles)))
if style == 'mpl-white':
try:
sns.set_style("whitegrid")
except:
pass
style = 'matplotlib'
if kwargs.get('savepath'):
mpl.rcParams['savefig.directory'] = kwargs.get('savepath')
kwargs.pop('savepath', None)
mpl.rcParams['savefig.bbox'] = 'tight'
mpl.rcParams.update({'figure.autolayout': True})
# try to use tex
# TO DO:
# make some font kwargs here
using_tex = False
mpl.rcParams['font.family'] = 'sans-serif'
mpl.rcParams['text.latex.unicode'] = True
if tex == 'try' or tex is True:
try:
rc('text', usetex=True)
rc('font', **{'family': 'serif', 'serif': ['Computer Modern']})
using_tex = True
except:
matplotlib.rc('font', family='sans-serif')
matplotlib.rc('font', serif='Helvetica Neue')
matplotlib.rc('text', usetex='false')
rc('text', usetex=False)
else:
rc('text', usetex=False)
if interactive:
using_tex = False
if show_totals is False:
show_totals = 'none'
# find out what kind of plot we're making, and enable
# or disable interactive values if need be
kwargs['kind'] = kind.lower()
if interactive:
if kwargs['kind'].startswith('bar'):
interactive_types = [3]
elif kwargs['kind'] == 'area':
interactive_types = [2, 3]
elif kwargs['kind'] == 'line':
interactive_types = [2, 3]
elif kwargs['kind'] == 'pie':
interactive_types = None
warnings.warn(
'Interactive plotting not yet available for pie plots.')
else:
interactive_types = [None]
if interactive is False:
interactive_types = [None]
# find out if pie mode, add autopct format
piemode = False
if kind == 'pie':
piemode = True
# always the best spot for pie
#if legend_pos == 'best':
#legend_pos = 'lower left'
if show_totals.endswith('plot') or show_totals.endswith('both'):
kwargs['pctdistance'] = 0.6
if using_tex:
kwargs['autopct'] = r'%1.1f\%%'
else:
kwargs['autopct'] = '%1.1f%%'
# copy data, make series into df
dataframe = df.copy()
if kind == 'heatmap':
try:
dataframe = dataframe.T
except:
pass
was_series = False
if isinstance(dataframe, Series):
was_series = True
if not cumulative:
dataframe = DataFrame(dataframe)
else:
dataframe = DataFrame(dataframe.cumsum())
else:
# don't know if this is much good.
if transpose:
dataframe = dataframe.T
if cumulative:
dataframe = DataFrame(dataframe.cumsum())
if len(list(dataframe.columns)) == 1:
was_series = True
# attempt to convert x axis to ints:
#try:
# dataframe.index = [int(i) for i in list(dataframe.index)]
#except:
# pass
# remove totals and tkinter order
if not was_series:
for name, ax in zip(['Total'] * 2 + ['tkintertable-order'] * 2,
[0, 1, 0, 1]):
try:
dataframe = dataframe.drop(name, axis=ax, errors='ignore')
except:
pass
try:
dataframe = dataframe.drop('tkintertable-order', errors='ignore')
except:
pass
try:
dataframe = dataframe.drop('tkintertable-order',
axis=1,
errors='ignore')
except:
pass
# look at columns to see if all can be ints, in which case, set up figure
# for depnumming
if not was_series:
if indices == 'guess':
def isint(x):
try:
a = float(x)
b = int(a)
except (ValueError, OverflowError):
return False
else:
return a == b
if all([isint(x) is True for x in list(dataframe.columns)]):
indices = True
else:
indices = False
# if depnumming, plot all, transpose, and rename axes
if indices is True:
num_to_plot = 'all'
dataframe = dataframe.T
if y_label is None:
y_label = 'Percentage of all matches'
if x_label is None:
x_label = ''
# set backend?
output_formats = [
'svgz', 'ps', 'emf', 'rgba', 'raw', 'pdf', 'svg', 'eps', 'png', 'pgf'
]
if output_format not in output_formats:
raise ValueError('%s output format not recognised. Must be: %s' %
(output_format, ', '.join(output_formats)))
# don't know if these are necessary
if 'pdf' in output_format:
plt.switch_backend(output_format)
if 'pgf' in output_format:
plt.switch_backend(output_format)
if num_to_plot == 'all':
if was_series:
if not piemode:
num_to_plot = len(dataframe)
else:
num_to_plot = len(dataframe)
else:
if not piemode:
num_to_plot = len(list(dataframe.columns))
else:
num_to_plot = len(dataframe.index)
# explode pie, or remove if not piemode
if piemode and not sbplt and kwargs.get('explode'):
kwargs['explode'] = auto_explode(dataframe,
kwargs['explode'],
was_series=was_series,
num_to_plot=num_to_plot)
else:
kwargs.pop('explode', None)
legend = kwargs.get('legend', True)
#cut data short
plotting_a_totals_column = False
if was_series:
if list(dataframe.columns)[0] != 'Total':
try:
can_be_ints = [int(x) for x in list(dataframe.index)]
num_to_plot = len(dataframe)
except:
dataframe = dataframe[:num_to_plot]
elif list(dataframe.columns)[0] == 'Total':
plotting_a_totals_column = True
if not 'legend' in kwargs:
legend = False
num_to_plot = len(dataframe)
else:
if transpose:
dataframe = dataframe.head(num_to_plot)
else:
dataframe = dataframe.T.head(num_to_plot).T
# remove stats fields, put p in entry text, etc.
statfields = ['slope', 'intercept', 'r', 'p', 'stderr']
try:
dataframe = dataframe.drop(statfields, axis=1, errors='ignore')
except:
pass
try:
dataframe.ix['p']
there_are_p_vals = True
except:
there_are_p_vals = False
if show_p_val:
if there_are_p_vals:
newnames = []
for col in list(dataframe.columns):
pval = dataframe[col]['p']
def p_string_formatter(val):
if val < 0.001:
if not using_tex:
return 'p < 0.001'
else:
return r'p $<$ 0.001'
else:
return 'p = %s' % format(val, '.3f')
pstr = p_string_formatter(pval)
newname = '%s (%s)' % (col, pstr)
newnames.append(newname)
dataframe.columns = newnames
dataframe.drop(statfields, axis=0, inplace=True, errors='ignore')
else:
warnings.warn(
'No p-values calculated to show.\n\nUse keep_stats kwarg while editing to generate these values.'
)
else:
if there_are_p_vals:
dataframe.drop(statfields, axis=0, inplace=True, errors='ignore')
# make and set y label
absolutes = True
if isinstance(dataframe, DataFrame):
try:
if not all([s.is_integer() for s in dataframe.iloc[0, :].values]):
absolutes = False
except:
pass
else:
if not all([s.is_integer() for s in dataframe.values]):
absolutes = False
##########################################
################ COLOURS #################
##########################################
# set defaults, with nothing for heatmap yet
if colours is True or colours == 'default' or colours == 'Default':
if kind != 'heatmap':
colours = 'viridis'
else:
colours = 'default'
# assume it's a single color, unless string denoting map
cmap_or_c = 'color'
if isinstance(colours, str):
cmap_or_c = 'colormap'
from matplotlib.colors import LinearSegmentedColormap
if isinstance(colours, LinearSegmentedColormap):
cmap_or_c = 'colormap'
# for heatmaps, it's always a colormap
if kind == 'heatmap':
cmap_or_c = 'cmap'
# if it's a defaulty string, set accordingly
if isinstance(colours, str):
if colours.lower().startswith('diverg'):
colours = sns.diverging_palette(10, 133, as_cmap=True)
# if default not set, do diverge for any df with a number < 0
elif colours.lower() == 'default':
mn = dataframe.min()
if isinstance(mn, Series):
mn = mn.min()
if mn < 0:
colours = sns.diverging_palette(10, 133, as_cmap=True)
else:
colours = sns.light_palette("green", as_cmap=True)
if 'seaborn' not in style:
kwargs[cmap_or_c] = colours
#if not was_series:
# if kind in ['pie', 'line', 'area']:
# if colours and not plotting_a_totals_column:
# kwargs[cmap_or_c] = colours
# else:
# if colours:
# kwargs[cmap_or_c] = colours
#if piemode:
# if num_to_plot > 0:
# kwargs[cmap_or_c] = colours
# else:
# if num_to_plot > 0:
# kwargs[cmap_or_c] = colours
# multicoloured bar charts
#if colours and cmap_or_c == 'colormap':
# if kind.startswith('bar'):
# if len(list(dataframe.columns)) == 1:
# if not black_and_white:
# import numpy as np
# the_range = np.linspace(0, 1, num_to_plot)
# middle = len(the_range) / 2
# try:
# cmap = plt.get_cmap(colours)
# kwargs[cmap_or_c] = [cmap(n) for n in the_range][middle]
# except ValueError:
# kwargs[cmap_or_c] = colours
# # make a bar width ... ? ...
# #kwargs['width'] = (figsize[0] / float(num_to_plot)) / 1.5
# reversing legend option
if reverse_legend is True:
rev_leg = True
elif reverse_legend is False:
rev_leg = False
# show legend or don't, guess whether to reverse based on kind
if kind in ['bar', 'barh', 'area', 'line', 'pie']:
if was_series:
legend = False
if kind == 'pie':
if pie_legend:
legend = True
else:
legend = False
if kind in ['barh', 'area']:
if reverse_legend == 'guess':
rev_leg = True
if not 'rev_leg' in locals():
rev_leg = False
# the default legend placement
if legend_pos is True:
legend_pos = 'best'
# cut dataframe if just_totals
try:
tst = dataframe['Combined total']
dataframe = dataframe.head(num_to_plot)
except:
pass
# no title for subplots because ugly,
if title and not sbplt:
kwargs['title'] = title
# no interactive subplots yet:
if sbplt and interactive:
import warnings
interactive = False
warnings.warn('No interactive subplots yet, sorry.')
return
# not using pandas for labels or legend anymore.
#kwargs['labels'] = None
#kwargs['legend'] = False
if legend:
if num_to_plot > 6:
if not kwargs.get('ncol'):
kwargs['ncol'] = num_to_plot // 7
# kwarg options go in leg_options
leg_options = {
'framealpha': leg_alpha,
'shadow': kwargs.get('shadow', False),
'ncol': kwargs.pop('ncol', 1)
}
# determine legend position based on this dict
if legend_pos:
possible = {
'best': 0,
'upper right': 1,
'upper left': 2,
'lower left': 3,
'lower right': 4,
'right': 5,
'center left': 6,
'center right': 7,
'lower center': 8,
'upper center': 9,
'center': 10,
'o r': 2,
'outside right': 2,
'outside upper right': 2,
'outside center right': 'center left',
'outside lower right': 'lower left'
}
if isinstance(legend_pos, int):
the_loc = legend_pos
elif isinstance(legend_pos, str):
try:
the_loc = possible[legend_pos]
except KeyError:
raise KeyError(
'legend_pos value must be one of:\n%s\n or an int between 0-10.'
% ', '.join(list(possible.keys())))
leg_options['loc'] = the_loc
#weirdness needed for outside plot
if legend_pos in ['o r', 'outside right', 'outside upper right']:
leg_options['bbox_to_anchor'] = (1.02, 1)
if legend_pos == 'outside center right':
leg_options['bbox_to_anchor'] = (1.02, 0.5)
if legend_pos == 'outside lower right':
leg_options['loc'] == 'upper right'
leg_options['bbox_to_anchor'] = (0.5, 0.5)
# a bit of distance between legend and plot for outside legends
if isinstance(legend_pos, str):
if legend_pos.startswith('o'):
leg_options['borderaxespad'] = 1
if not piemode:
if show_totals.endswith('both') or show_totals.endswith('legend'):
dataframe = rename_data_with_total(dataframe,
was_series=was_series,
using_tex=using_tex,
absolutes=absolutes)
else:
if pie_legend:
if show_totals.endswith('both') or show_totals.endswith('legend'):
dataframe = rename_data_with_total(dataframe,
was_series=was_series,
using_tex=using_tex,
absolutes=absolutes)
if piemode:
if partial_pie:
dataframe = dataframe / 100.0
# some pie things
if piemode:
if not sbplt:
kwargs['y'] = list(dataframe.columns)[0]
def filler(df):
pby = df.T.copy()
for i in list(pby.columns):
tot = pby[i].sum()
pby[i] = pby[i] * 100.0 / tot
return pby.T
areamode = False
if kind == 'area':
areamode = True
if legend is False:
kwargs['legend'] = False
# line highlighting option for interactive!
if interactive:
if 2 in interactive_types:
if kind == 'line':
kwargs['marker'] = ','
if not piemode:
kwargs['alpha'] = 0.1
# convert dates --- works only in my current case!
#if plotting_a_totals_column or not was_series:
# try:
# can_it_be_int = int(list(dataframe.index)[0])
# can_be_int = True
# except:
# can_be_int = False
# if can_be_int:
# if 1500 < int(list(dataframe.index)[0]):
# if 2050 > int(list(dataframe.index)[0]):
# n = pandas.PeriodIndex([d for d in list(dataframe.index)], freq='A')
# dataframe = dataframe.set_index(n)
if kwargs.get('filled'):
if areamode or kind.startswith('bar'):
dataframe = filler(dataframe)
kwargs.pop('filled', None)
MARKERSIZE = 4
COLORMAP = {
0: {
'marker': None,
'dash': (None, None)
},
1: {
'marker': None,
'dash': [5, 5]
},
2: {
'marker': "o",
'dash': (None, None)
},
3: {
'marker': None,
'dash': [1, 3]
},
4: {
'marker': "s",
'dash': [5, 2, 5, 2, 5, 10]
},
5: {
'marker': None,
'dash': [5, 3, 1, 2, 1, 10]
},
6: {
'marker': 'o',
'dash': (None, None)
},
7: {
'marker': None,
'dash': [5, 3, 1, 3]
},
8: {
'marker': "1",
'dash': [1, 3]
},
9: {
'marker': "*",
'dash': [5, 5]
},
10: {
'marker': "2",
'dash': [5, 2, 5, 2, 5, 10]
},
11: {
'marker': "s",
'dash': (None, None)
}
}
HATCHES = {
0: {
'color': '#dfdfdf',
'hatch': "/"
},
1: {
'color': '#6f6f6f',
'hatch': "\\"
},
2: {
'color': 'b',
'hatch': "|"
},
3: {
'color': '#dfdfdf',
'hatch': "-"
},
4: {
'color': '#6f6f6f',
'hatch': "+"
},
5: {
'color': 'b',
'hatch': "x"
}
}
if black_and_white:
if kind == 'line':
kwargs['linewidth'] = 1
cmap = plt.get_cmap('Greys')
new_cmap = truncate_colormap(cmap, 0.25, 0.95)
if kind == 'bar':
# darker if just one entry
if len(dataframe.columns) == 1:
new_cmap = truncate_colormap(cmap, 0.70, 0.90)
kwargs[cmap_or_c] = new_cmap
# remove things from kwargs if heatmap
if kind == 'heatmap':
hmargs = {
'annot': kwargs.pop('annot', True),
cmap_or_c: kwargs.pop(cmap_or_c, None),
'fmt': kwargs.pop('fmt', ".2f"),
'cbar': kwargs.pop('cbar', False)
}
for i in [
'vmin', 'vmax', 'linewidths', 'linecolor', 'robust', 'center',
'cbar_kws', 'cbar_ax', 'square', 'mask', 'norm'
]:
if i in kwargs.keys():
hmargs[i] = kwargs.pop(i, None)
class dummy_context_mgr():
"""a fake context for plotting without style
perhaps made obsolete by 'classic' style in new mpl"""
def __enter__(self):
return None
def __exit__(self, one, two, three):
return False
with plt.style.context(
(style)) if style != 'matplotlib' else dummy_context_mgr():
kwargs.pop('filled', None)
if not sbplt:
# check if negative values, no stacked if so
if areamode:
if not kwargs.get('ax'):
kwargs['legend'] = False
if dataframe.applymap(lambda x: x < 0.0).any().any():
kwargs['stacked'] = False
rev_leg = False
if kind != 'heatmap':
# turn off pie labels at the last minute
if kind == 'pie' and pie_legend:
kwargs['labels'] = None
kwargs['autopct'] = '%.2f'
if kind == 'pie':
kwargs.pop('color', None)
ax = dataframe.plot(figsize=figsize, **kwargs)
else:
fg = plt.figure(figsize=figsize)
if title:
plt.title(title)
ax = kwargs.get('ax', plt.axes())
tmp = sns.heatmap(dataframe, ax=ax, **hmargs)
ax.set_title(title)
for item in tmp.get_yticklabels():
item.set_rotation(0)
plt.close(fg)
if areamode and not kwargs.get('ax'):
handles, labels = plt.gca().get_legend_handles_labels()
del handles
del labels
if x_label:
ax.set_xlabel(x_label)
if y_label:
ax.set_ylabel(y_label)
else:
if not kwargs.get('layout'):
plt.gcf().set_tight_layout(False)
if kind != 'heatmap':
ax = dataframe.plot(figsize=figsize, **kwargs)
else:
plt.figure(figsize=figsize)
if title:
plt.title(title)
ax = plt.axes()
sns.heatmap(dataframe, ax=ax, **hmargs)
plt.xticks(rotation=0)
plt.yticks(rotation=0)
def rotate_degrees(rotation, labels):
if rotation is None:
if max(labels, key=len) > 6:
return 45
else:
return 0
elif rotation is False:
return 0
elif rotation is True:
return 45
else:
return rotation
if sbplt:
if 'layout' not in kwargs:
axes = [l for l in ax]
else:
axes = []
cols = [l for l in ax]
for col in cols:
for bit in col:
axes.append(bit)
for index, a in enumerate(axes):
if xtickspan is not False:
a.xaxis.set_major_locator(
ticker.MultipleLocator(xtickspan))
labels = [item.get_text() for item in a.get_xticklabels()]
rotation = rotate_degrees(the_rotation, labels)
try:
if the_rotation == 0:
ax.set_xticklabels(labels,
rotation=rotation,
ha='center')
else:
ax.set_xticklabels(labels,
rotation=rotation,
ha='right')
except AttributeError:
pass
else:
if kind == 'heatmap':
labels = [item.get_text() for item in ax.get_xticklabels()]
rotation = rotate_degrees(the_rotation, labels)
if the_rotation == 0:
ax.set_xticklabels(labels, rotation=rotation, ha='center')
else:
ax.set_xticklabels(labels, rotation=rotation, ha='right')
if transparent:
plt.gcf().patch.set_facecolor('white')
plt.gcf().patch.set_alpha(0)
if black_and_white:
if kind == 'line':
# white background
# change everything to black and white with interesting dashes and markers
c = 0
for line in ax.get_lines():
line.set_color('black')
#line.set_width(1)
line.set_dashes(COLORMAP[c]['dash'])
line.set_marker(COLORMAP[c]['marker'])
line.set_markersize(MARKERSIZE)
c += 1
if c == len(list(COLORMAP.keys())):
c = 0
# draw legend with proper placement etc
if legend:
if not piemode and not sbplt and kind != 'heatmap':
if 3 not in interactive_types:
handles, labels = plt.gca().get_legend_handles_labels()
# area doubles the handles and labels. this removes half:
#if areamode:
# handles = handles[-len(handles) / 2:]
# labels = labels[-len(labels) / 2:]
if rev_leg:
handles = handles[::-1]
labels = labels[::-1]
if kwargs.get('ax'):
lgd = plt.gca().legend(handles, labels, **leg_options)
ax.get_legend().draw_frame(leg_frame)
else:
lgd = plt.legend(handles, labels, **leg_options)
lgd.draw_frame(leg_frame)
if interactive:
# 1 = highlight lines
# 2 = line labels
# 3 = legend switches
ax = plt.gca()
# fails for piemode
lines = ax.lines
handles, labels = plt.gca().get_legend_handles_labels()
if 1 in interactive_types:
plugins.connect(plt.gcf(), HighlightLines(lines))
if 3 in interactive_types:
plugins.connect(
plt.gcf(),
InteractiveLegendPlugin(lines, labels, alpha_unsel=0.0))
for i, l in enumerate(lines):
y_vals = l.get_ydata()
x_vals = l.get_xdata()
x_vals = [str(x) for x in x_vals]
if absolutes:
ls = [
'%s (%s: %d)' % (labels[i], x_val, y_val)
for x_val, y_val in zip(x_vals, y_vals)
]
else:
ls = [
'%s (%s: %.2f%%)' % (labels[i], x_val, y_val)
for x_val, y_val in zip(x_vals, y_vals)
]
if 2 in interactive_types:
#if 'kind' in kwargs and kwargs['kind'] == 'area':
tooltip_line = mpld3.plugins.LineLabelTooltip(
lines[i], labels[i])
mpld3.plugins.connect(plt.gcf(), tooltip_line)
#else:
if kind == 'line':
tooltip_point = mpld3.plugins.PointLabelTooltip(l,
labels=ls)
mpld3.plugins.connect(plt.gcf(), tooltip_point)
if piemode:
if not sbplt:
plt.axis('equal')
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
# add x label
# this could be revised now!
# if time series period, it's year for now
if isinstance(dataframe.index, pandas.tseries.period.PeriodIndex):
x_label = 'Year'
y_l = False
if not absolutes:
y_l = 'Percentage'
else:
y_l = 'Absolute frequency'
# hacky: turn legend into subplot titles :)
if sbplt:
# title the big plot
#plt.gca().suptitle(title, fontsize = 16)
#plt.subplots_adjust(top=0.9)
# get all axes
if 'layout' not in kwargs:
axes = [l for index, l in enumerate(ax)]
else:
axes = []
cols = [l for index, l in enumerate(ax)]
for col in cols:
for bit in col:
axes.append(bit)
# set subplot titles
for index, a in enumerate(axes):
try:
titletext = list(dataframe.columns)[index]
except:
pass
a.set_title(titletext)
try:
a.legend_.remove()
except:
pass
#try:
# from matplotlib.ticker import MaxNLocator
# from corpkit.process import is_number
# indx = list(dataframe.index)
# if all([is_number(qq) for qq in indx]):
# ax.get_xaxis().set_major_locator(MaxNLocator(integer=True))
#except:
# pass
# remove axis labels for pie plots
if piemode:
a.axes.get_xaxis().set_visible(False)
a.axes.get_yaxis().set_visible(False)
a.axis('equal')
a.grid(b=show_grid)
# add sums to bar graphs and pie graphs
# doubled right now, no matter
if not sbplt:
# show grid
ax.grid(b=show_grid)
if kind.startswith('bar'):
width = ax.containers[0][0].get_width()
if was_series:
the_y_limit = plt.ylim()[1]
if show_totals.endswith('plot') or show_totals.endswith('both'):
# make plot a bit higher if putting these totals on it
plt.ylim([0, the_y_limit * 1.05])
for i, label in enumerate(list(dataframe.index)):
if len(dataframe.ix[label]) == 1:
score = dataframe.ix[label][0]
else:
if absolutes:
score = dataframe.ix[label].sum()
else:
#import warnings
#warnings.warn("It's not possible to determine total percentage from individual percentages.")
continue
if not absolutes:
plt.annotate('%.2f' % score, (i, score),
ha='center',
va='bottom')
else:
plt.annotate(score, (i, score), ha='center', va='bottom')
else:
the_y_limit = plt.ylim()[1]
if show_totals.endswith('plot') or show_totals.endswith('both'):
for i, label in enumerate(list(dataframe.columns)):
if len(dataframe[label]) == 1:
score = dataframe[label][0]
else:
if absolutes:
score = dataframe[label].sum()
else:
#import warnings
#warnings.warn("It's not possible to determine total percentage from individual percentages.")
continue
if not absolutes:
plt.annotate('%.2f' % score, (i, score),
ha='center',
va='bottom')
else:
plt.annotate(score, (i, score), ha='center', va='bottom')
if not kwargs.get('layout') and not sbplt and not kwargs.get('ax'):
plt.tight_layout()
if kwargs.get('ax'):
try:
plt.gcf().set_tight_layout(False)
except:
pass
try:
plt.set_tight_layout(False)
except:
pass
if save:
if running_python_tex:
imagefolder = '../images'
else:
imagefolder = 'images'
savename = get_savename(imagefolder,
save=save,
title=title,
ext=output_format)
if not os.path.isdir(imagefolder):
os.makedirs(imagefolder)
# save image and get on with our lives
if legend_pos.startswith('o') and not sbplt:
plt.gcf().savefig(savename,
dpi=150,
bbox_extra_artists=(lgd, ),
bbox_inches='tight',
format=output_format)
else:
plt.gcf().savefig(savename, dpi=150, format=output_format)
time = strftime("%H:%M:%S", localtime())
if os.path.isfile(savename):
print('\n' + time + ": " + savename + " created.")
else:
raise ValueError("Error making %s." % savename)
if dragmode:
plt.legend().draggable()
if sbplt:
plt.subplots_adjust(right=.8)
plt.subplots_adjust(left=.1)
# add DataCursor to notebook backend if possible
if have_mpldc:
if kind == 'line':
HighlightingDataCursor(
plt.gca().get_lines(),
highlight_width=4,
highlight_color=False,
formatter=lambda **kwargs: '%s: %s' %
(kwargs['label'], "{0:.3f}".format(kwargs['y'])))
else:
datacursor(formatter=lambda **kwargs: '%s: %s' %
(kwargs['label'], "{0:.3f}".format(kwargs['height'])))
#if not interactive and not running_python_tex and not running_spider \
# and not tk:
# plt.gcf().show()
# return plt
#elif running_spider or tk:
# return plt
if interactive:
plt.subplots_adjust(right=.8)
plt.subplots_adjust(left=.1)
try:
ax.legend_.remove()
except:
pass
return mpld3.display()
else:
return plt
def buildGraph2(self):
self.load_tfidf()
cPaths = Paths(self.folder)
self.filenames, self.folders = cPaths.getTxts()
xs, ys = self.loadMDS()
# xs, ys = self.create_MDS()
cluster_colors, cluster_names = self.setClusters()
#create data frame that has the result of the MDS plus the cluster numbers and titles
df = pd.DataFrame(
dict(x=xs, y=ys, label=self.clusters(), title=self.filenames))
#group by cluster
groups = df.groupby('label')
#define custom css to format the font and to remove the axis labeling
css = """
text.mpld3-text, div.mpld3-tooltip {
font-family:Arial, Helvetica, sans-serif;
}
g.mpld3-xaxis, g.mpld3-yaxis {
display: none; }
svg.mpld3-figure {
margin-left: -200px;}
"""
# Plot
fig, ax = plt.subplots(figsize=(14, 6)) #set plot size
ax.margins(0.03) # Optional, just adds 5% padding to the autoscaling
#iterate through groups to layer the plot
#note that I use the cluster_name and cluster_color dicts with the 'name' lookup to return the appropriate color/label
for name, group in groups:
points = ax.plot(group.x,
group.y,
marker='o',
linestyle='',
ms=18,
label=cluster_names[name],
mec='none',
color=cluster_colors[name])
ax.set_aspect('auto')
labels = [i for i in group.title]
#set tooltip using points, labels and the already defined 'css'
tooltip = mpld3.plugins.PointHTMLTooltip(points[0],
labels,
voffset=10,
hoffset=10,
css=css)
#connect tooltip to fig
mpld3.plugins.connect(fig, tooltip, TopToolbar())
#set tick marks as blank
ax.axes.get_xaxis().set_ticks([])
ax.axes.get_yaxis().set_ticks([])
#set axis as blank
ax.axes.get_xaxis().set_visible(False)
ax.axes.get_yaxis().set_visible(False)
ax.legend(numpoints=1) #show legend with only one dot
mpld3.display() #show the plot
def plotEssays(x,
y,
labels,
titles,
cluster_names=None,
ms=10,
output='notebook'):
#create data frame that has the result of the MDS plus the cluster numbers and titles
df = pd.DataFrame(dict(x=x, y=y, label=labels, title=titles))
#group by cluster
groups = df.groupby('label')
#define custom css to format the font and to remove the axis labeling
css = """
text.mpld3-text, div.mpld3-tooltip {
font-family:Arial, Helvetica, sans-serif;
}
g.mpld3-xaxis, g.mpld3-yaxis {
display: none; }
svg.mpld3-figure {
margin-left: -100px;
margin-right: -100px}
"""
#set up colors per clusters using a dict
# cluster_colors = {0: '#1b9e77', 1: '#d95f02', 2: '#7570b3', 3: '#e7298a', 4: '#66a61e', 5: 'b', 6: 'g', 7:'r'}
#set up cluster names using a dict
if cluster_names is None:
cluster_names = {x: x for x in xrange(len(set(labels)))}
# Plot
if output == 'notebook':
fig, ax = plt.subplots(figsize=(14, 6)) #set plot size
elif output == 'app':
fig, ax = plt.subplots(figsize=(14, 8))
ax.margins(0.03) # Optional, just adds 5% padding to the autoscaling
#iterate through groups to layer the plot
#note that I use the cluster_name and cluster_color dicts with the 'name' lookup to return the appropriate color/label
for name, group in groups:
points = ax.plot(group.x,
group.y,
marker='o',
linestyle='',
ms=ms,
label=cluster_names[name],
mec='none')
ax.set_aspect('auto')
labels = [i for i in group.title]
#set tooltip using points, labels and the already defined 'css'
tooltip = mpld3.plugins.PointHTMLTooltip(points[0],
labels,
voffset=10,
hoffset=10,
css=css)
#connect tooltip to fig
mpld3.plugins.connect(fig, tooltip, TopToolbar())
#set tick marks as blank
ax.axes.get_xaxis().set_ticks([])
ax.axes.get_yaxis().set_ticks([])
#set axis as blank
ax.axes.get_xaxis().set_visible(True)
ax.axes.get_yaxis().set_visible(True)
ax.legend(numpoints=1) #show legend with only one dot
# ax.legend(loc='upper center', bbox_to_anchor=(0.5, -0.05),
# fancybox=True, shadow=True, ncol=7)
if output == 'notebook':
return mpld3.display()
elif output == 'app':
html = mpld3.fig_to_html(fig)
return html
# Para plotar polcgonos
def plot_polygon(ax, vertices, color_index, to_fill = False):
color = get_tab10_color_from_index(color_index)
points_series = [[vertex.x,vertex.y] for vertex in vertices]
polygon = patches.Polygon(points_series,linewidth=1,edgecolor=color,fill=color if to_fill else None)
ax.add_patch(polygon)
# Para anotar texto sobre a plotagem
def annotate(text, vertex):
plt.annotate(text, (vertex.x, vertex.y))
# Para renderizar a plotagem
plot = lambda: mpld3.display()
# Para capturar texto de palavra
def get_word_text(word):
return ''.join([symbol.text for symbol in word.symbols])
## Plotando palavras encontradas
from PIL import Image
image_data = Image.open(image_path)
ax = prepare_image_data(image_data)
for item_index, word in enumerate(all_words):
plt.title(f'{image_path} words')
def pretty_draw(g):
css = """
table
{
border-collapse: collapse;
}
th
{
color: #ffffff;
background-color: #000000;
}
td
{
background-color: #cccccc;
}
table, th, td
{
font-family:Arial, Helvetica, sans-serif;
border: 1px solid black;
text-align: center;
padding: 3px;
font-size:11pt;
}
g.mpld3-xaxis, g.mpld3-yaxis {
display: none;
}
"""
fig = plt.figure(figsize=(12, 8))
ax = plt.gca()
nodes = []
edges = list(g.edges())
layout = nx.spring_layout(g, iterations=10)
points = []
labels = []
for node, (x, y) in layout.items():
nodes.append(node)
points.append((x, y))
try:
try:
labels.append(g.cpd(node)._repr_html_())
except:
labels.append(str(g.cpd(node)))
except:
pass
points_x, points_y = zip(*points)
ax.set_xlim(min(points_x) - 0.08, max(points_x) + 0.08)
ax.set_ylim(min(points_y) - 0.08, max(points_y) + 0.08)
for src, dst in edges:
src_pos = layout[src]
dst_pos = layout[dst]
arr_pos = dst_pos - 0.15*(dst_pos - src_pos)
ax.plot(*list(zip(src_pos, dst_pos)), color='grey')
ax.plot(*list(zip(arr_pos, dst_pos)), color='black', alpha=.5, linewidth=5)
ax.plot(points_x, points_y, 'o', color='lightgray',
mec='k', ms=20, mew=1, alpha=1.)
for text, x, y in zip(nodes, points_x, points_y):
ax.text(x, y, text, horizontalalignment='center', verticalalignment='center')
pts = ax.plot(points_x, points_y, 'o', color='lightgray',
mec='k', ms=40, mew=1, alpha=0.)
tooltip = plugins.PointHTMLTooltip(pts[0], labels,
voffset=10, hoffset=10, css=css)
plugins.connect(fig, tooltip)
return mpld3.display()
def cluster_graphic_html():
MDS()
# two components as we're plotting points in a two-dimensional plane
# "precomputed" because we provide a distance matrix
# we will also specify `random_state` so the plot is reproducible.
mds = MDS(n_components=2, dissimilarity="precomputed", random_state=1)
pos = mds.fit_transform(model.dist) # shape (n_components, n_samples)
xs, ys = pos[:, 0], pos[:, 1]
clusters = model.KMmodel.labels_.tolist()
#create data frame that has the result of the MDS plus the cluster numbers and titles
df = pd.DataFrame(dict(x=xs, y=ys, label=clusters, title=model.titles))
#group by cluster
groups = df.groupby('label')
#define custom css to format the font and to remove the axis labeling
css = """
text.mpld3-text, div.mpld3-tooltip {
font-family:Arial, Helvetica, sans-serif;
}
g.mpld3-xaxis, g.mpld3-yaxis {
display: none; }
"""
# Plot
fig, ax = plt.subplots(figsize=(14,6)) #set plot size
ax.margins(0.03) # Optional, just adds 5% padding to the autoscaling
#set up colors per clusters using a dict
cluster_colors = {0: '#1b9e77', 1: '#d95f02', 2: '#7570b3', 3: '#e7298a', 4: '#66a61e'}
#set up cluster names using a dict
cluster_names = {0: 'Family, home, war',
1: 'Police, killed, murders',
2: 'Father, New York, brothers',
3: 'Dance, singing, love',
4: 'Killed, soldiers, captain'}
#iterate through groups to layer the plot
#note that I use the cluster_name and cluster_color dicts with the 'name' lookup to return the appropriate color/label
for name, group in groups:
points = ax.plot(group.x, group.y, marker='o', linestyle='', ms=18, label=cluster_names[name], mec='none', color=cluster_colors[name])
ax.set_aspect('auto')
labels = [i for i in group.title]
#set tooltip using points, labels and the already defined 'css'
tooltip = mpld3.plugins.PointHTMLTooltip(points[0], labels,
voffset=10, hoffset=10, css=css)
#connect tooltip to fig
mpld3.plugins.connect(fig, tooltip, TopToolbar())
#set tick marks as blank
ax.axes.get_xaxis().set_ticks([])
ax.axes.get_yaxis().set_ticks([])
#set axis as blank
ax.axes.get_xaxis().set_visible(False)
ax.axes.get_yaxis().set_visible(False)
ax.legend(numpoints=1) #show legend with only one dot
mpld3.display() #show the plot
#uncomment the below to export to html
html = mpld3.fig_to_html(fig)
return html
fig, ax = plt.subplots(subplot_kw=dict(facecolor='#f2f6fc'))
for i in [duration]:
x = timestamp
y = duration
scatter = ax.scatter(x,
y,
c=i,
alpha=0.5,
edgecolors='none',
cmap=plt.cm.jet,
label=l)
ax.grid(color='white', linestyle='solid')
ax.set_title("MarkLogic Slow Queries", size=20)
ax.set_xlabel('Timestamp',
fontsize=12,
fontdict={'family': 'monospace'},
labelpad=5)
ax.set_ylabel('Query Duration (secs)',
fontsize=12,
fontdict={'family': 'monospace'},
labelpad=10)
tooltip = mpld3.plugins.PointLabelTooltip(scatter)
mpld3.plugins.connect(fig, tooltip)
mpld3.display()
#plt.show()
# nom_list = ['Sessions','Flynn','Gorsuch','Trump']
# color_list = ['b','r']
# useful list -> ['Russia','Trumpcare','MuslimBan']
nom_list = ['Sessions', 'Flynn', 'Gorsuch', 'Trump']
color_list = ['b', 'r', 'g', 'k']
# fig = plt.axes()
for nom, color in zip(nom_list, color_list):
mention_counts = []
dates = []
for n in files:
date_string = n[11:-5]
dt_string = dt.strptime(date_string, '%Y-%m-%d')
dates.append(dt_string)
mention_count = nom_mentions(n, nom)
mention_counts.append(mention_count)
# print(dates)
# print(mention_counts)
plt.plot(dates, mention_counts, color)
# fig.plot(dates, mention_counts, color)
plt.legend(nom_list)
# fig.legend(nom_list)
plt.title('Phone Number Tweets by Names')
plt.legend(nom_list)
# fig.set_title('Phone Number Tweets by Names')
mpld3.display(plt)
# plt.show()
def plotter(title,
df,
x_label = None,
y_label = None,
style = 'ggplot',
figsize = (8, 4),
save = False,
legend_pos = 'best',
reverse_legend = 'guess',
num_to_plot = 7,
tex = 'try',
colours = 'Paired',
cumulative = False,
pie_legend = True,
partial_pie = False,
show_totals = False,
transparent = False,
output_format = 'png',
interactive = False,
black_and_white = False,
show_p_val = False,
indices = 'guess',
**kwargs):
"""plot interrogator() or editor() output.
**kwargs are for pandas first, which can then send them through to matplotlib.plot():
http://pandas.pydata.org/pandas-docs/dev/generated/pandas.DataFrame.plot.html
http://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.plot
pie_legend: False to label slices rather than give legend
show_totals: where to show percent/abs frequencies: False, 'plot', 'legend', or 'both'
"""
import corpkit
import os
import matplotlib as mpl
if interactive:
import matplotlib.pyplot as plt, mpld3
else:
import matplotlib.pyplot as plt
from matplotlib import rc
import pandas
import pandas as pd
from pandas import DataFrame
import numpy
from time import localtime, strftime
from corpkit.tests import check_pytex, check_spider, check_t_kinter
if interactive:
import mpld3
import collections
from mpld3 import plugins, utils
from plugins import InteractiveLegendPlugin, HighlightLines
tk = check_t_kinter()
running_python_tex = check_pytex()
# incorrect spelling of spider on purpose
running_spider = check_spider()
def truncate_colormap(cmap, minval=0.0, maxval=1.0, n=100):
"""remove extreme values from colourmap --- no pure white"""
import matplotlib.colors as colors
import numpy as np
new_cmap = colors.LinearSegmentedColormap.from_list(
'trunc({n},{a:.2f},{b:.2f})'.format(n=cmap.name, a=minval, b=maxval),
cmap(np.linspace(minval, maxval, n)))
return new_cmap
def get_savename(imagefolder, save = False, title = False, ext = 'png'):
"""Come up with the savename for the image."""
import os
def urlify(s):
"Turn title into filename"
import re
s = s.lower()
s = re.sub(r"[^\w\s-]", '', s)
s = re.sub(r"\s+", '-', s)
s = re.sub(r"-(textbf|emph|textsc|textit)", '-', s)
return s
# name as
if not ext.startswith('.'):
ext = '.' + ext
if type(save) == str:
savename = os.path.join(imagefolder, (urlify(save) + ext))
#this 'else' is redundant now that title is obligatory
else:
if title:
filename = urlify(title) + ext
savename = os.path.join(imagefolder, filename)
# remove duplicated ext
if savename.endswith('%s%s' % (ext, ext)):
savename = savename.replace('%s%s' % (ext, ext), ext, 1)
return savename
def rename_data_with_total(dataframe, was_series = False, using_tex = False, absolutes = True):
"""adds totals (abs, rel, keyness) to entry name strings"""
if was_series:
where_the_words_are = dataframe.index
else:
where_the_words_are = dataframe.columns
the_labs = []
for w in list(where_the_words_are):
if not absolutes:
if was_series:
perc = dataframe.T[w][0]
else:
the_labs.append(w)
continue
if using_tex:
the_labs.append('%s (%.2f\%%)' % (w, perc))
else:
the_labs.append('%s (%.2f %%)' % (w, perc))
else:
if was_series:
score = dataframe.T[w].sum()
else:
score = dataframe[w].sum()
if using_tex:
the_labs.append('%s (n=%d)' % (w, score))
else:
the_labs.append('%s (n=%d)' % (w, score))
if not was_series:
dataframe.columns = the_labs
else:
vals = list(dataframe[list(dataframe.columns)[0]].values)
dataframe = pd.DataFrame(vals, index = the_labs)
dataframe.columns = ['Total']
return dataframe
def auto_explode(dataframe, input, was_series = False, num_to_plot = 7):
"""give me a list of strings and i'll output explode option"""
output = [0 for s in range(num_to_plot)]
if was_series:
l = list(dataframe.index)
else:
l = list(dataframe.columns)
if type(input) == str or type(input) == int:
input = [input]
if type(input) == list:
for i in input:
if type(i) == str:
index = l.index(i)
else:
index = i
output[index] = 0.1
return output
# are we doing subplots?
sbplt = False
if 'subplots' in kwargs:
if kwargs['subplots'] is True:
sbplt = True
if colours is True:
colours = 'Paired'
styles = ['dark_background', 'bmh', 'grayscale', 'ggplot', 'fivethirtyeight']
if style not in styles:
raise ValueError('Style %s not found. Use %s' % (style, ', '.join(styles)))
if 'savepath' in kwargs.keys():
mpl.rcParams['savefig.directory'] = kwargs['savepath']
del kwargs['savepath']
mpl.rcParams['savefig.bbox'] = 'tight'
# try to use tex
# TO DO:
# make some font kwargs here
using_tex = False
mpl.rcParams['font.family'] = 'sans-serif'
mpl.rcParams['text.latex.unicode'] = True
if tex == 'try' or tex is True:
try:
rc('text', usetex=True)
rc('font', **{'family': 'serif', 'serif': ['Computer Modern']})
using_tex = True
except:
matplotlib.rc('font', family='sans-serif')
matplotlib.rc('font', serif='Helvetica Neue')
matplotlib.rc('text', usetex='false')
rc('text', usetex=False)
else:
rc('text', usetex=False)
if interactive:
using_tex = False
if show_totals is False:
show_totals = 'none'
# find out what kind of plot we're making, and enable
# or disable interactive values if need be
if 'kind' not in kwargs:
kwargs['kind'] = 'line'
if interactive:
if kwargs['kind'].startswith('bar'):
interactive_types = [3]
elif kwargs['kind'] == 'area':
interactive_types = [2, 3]
elif kwargs['kind'] == 'line':
interactive_types = [2, 3]
elif kwargs['kind'] == 'pie':
interactive_types = None
warnings.warn('Interactive plotting not yet available for pie plots.')
else:
interactive_types = [None]
if interactive is False:
interactive_types = [None]
# find out if pie mode, add autopct format
piemode = False
if 'kind' in kwargs:
if kwargs['kind'] == 'pie':
piemode = True
# always the best spot for pie
#if legend_pos == 'best':
#legend_pos = 'lower left'
if show_totals.endswith('plot') or show_totals.endswith('both'):
kwargs['pctdistance'] = 0.6
if using_tex:
kwargs['autopct'] = r'%1.1f\%%'
else:
kwargs['autopct'] = '%1.1f%%'
#if piemode:
#if partial_pie:
#kwargs['startangle'] = 180
kwargs['subplots'] = sbplt
# copy data, make series into df
dataframe = df.copy()
was_series = False
if type(dataframe) == pandas.core.series.Series:
was_series = True
if not cumulative:
dataframe = DataFrame(dataframe)
else:
dataframe = DataFrame(dataframe.cumsum())
else:
# don't know if this is much good.
if cumulative:
dataframe = DataFrame(dataframe.cumsum())
if len(list(dataframe.columns)) == 1:
was_series = True
# attempt to convert x axis to ints:
try:
dataframe.index = [int(i) for i in list(dataframe.index)]
except:
pass
# remove totals and tkinter order
if not was_series:
for name, ax in zip(['Total'] * 2 + ['tkintertable-order'] * 2, [0, 1, 0, 1]):
dataframe = dataframe.drop(name, axis = ax, errors = 'ignore')
else:
dataframe = dataframe.drop('tkintertable-order', errors = 'ignore')
dataframe = dataframe.drop('tkintertable-order', axis = 1, errors = 'ignore')
# look at columns to see if all can be ints, in which case, set up figure
# for depnumming
if not was_series:
if indices == 'guess':
def isint(x):
try:
a = float(x)
b = int(a)
except ValueError or OverflowError:
return False
else:
return a == b
if all([isint(x) is True for x in list(dataframe.columns)]):
indices = True
else:
indices = False
# if depnumming, plot all, transpose, and rename axes
if indices is True:
num_to_plot = 'all'
dataframe = dataframe.T
if y_label is None:
y_label = 'Percentage of all matches'
if x_label is None:
x_label = ''
# set backend?
output_formats = ['svgz', 'ps', 'emf', 'rgba', 'raw', 'pdf', 'svg', 'eps', 'png', 'pgf']
if output_format not in output_formats:
raise ValueError('%s output format not recognised. Must be: %s' % (output_format, ', '.join(output_formats)))
# don't know if these are necessary
if 'pdf' in output_format:
plt.switch_backend(output_format)
if 'pgf' in output_format:
plt.switch_backend(output_format)
if num_to_plot == 'all':
if was_series:
if not piemode:
num_to_plot = len(dataframe)
else:
num_to_plot = len(dataframe)
else:
if not piemode:
num_to_plot = len(list(dataframe.columns))
else:
num_to_plot = len(dataframe.index)
# explode pie, or remove if not piemode
if 'explode' in kwargs:
if not piemode:
del kwargs['explode']
if piemode:
if 'explode' in kwargs:
if not sbplt:
kwargs['explode'] = auto_explode(dataframe,
kwargs['explode'],
was_series = was_series,
num_to_plot = num_to_plot)
if 'legend' in kwargs:
legend = kwargs['legend']
else:
legend = True
#cut data short
plotting_a_totals_column = False
if was_series:
if list(dataframe.columns)[0] != 'Total':
try:
can_be_ints = [int(x) for x in list(dataframe.index)]
num_to_plot = len(dataframe)
except:
dataframe = dataframe[:num_to_plot]
elif list(dataframe.columns)[0] == 'Total':
plotting_a_totals_column = True
if not 'legend' in kwargs:
legend = False
num_to_plot = len(dataframe)
else:
dataframe = dataframe.T.head(num_to_plot).T
# remove stats fields, put p in entry text, etc.
statfields = ['slope', 'intercept', 'r', 'p', 'stderr']
try:
dataframe = dataframe.drop(statfields, axis = 1)
except:
pass
try:
dataframe.ix['p']
there_are_p_vals = True
except:
there_are_p_vals = False
if show_p_val:
if there_are_p_vals:
newnames = []
for col in list(dataframe.columns):
pval = dataframe[col]['p']
newname = '%s (p=%s)' % (col, format(pval, '.5f'))
newnames.append(newname)
dataframe.columns = newnames
dataframe.drop(statfields, axis = 0, inplace = True)
else:
warnings.warn('No p-values calculated to show.\n\nUse sort_by and keep_stats in editor() to generate these values.')
else:
if there_are_p_vals:
dataframe.drop(statfields, axis = 0, inplace = True)
# make and set y label
absolutes = True
if type(dataframe) == pandas.core.frame.DataFrame:
try:
if not all([s.is_integer() for s in dataframe.iloc[0,:].values]):
absolutes = False
except:
pass
else:
if not all([s.is_integer() for s in dataframe.values]):
absolutes = False
# use colormap if need be:
if num_to_plot > 0:
if not was_series:
if 'kind' in kwargs:
if kwargs['kind'] in ['pie', 'line', 'area']:
if colours:
if not plotting_a_totals_column:
if colours == 'Default':
colours = 'Paired'
kwargs['colormap'] = colours
#else:
if colours:
if colours == 'Default':
colours = 'Paired'
kwargs['colormap'] = colours
if piemode:
if num_to_plot > 0:
if colours == 'Default':
colours = 'Paired'
kwargs['colormap'] = colours
else:
if num_to_plot > 0:
if colours == 'Default':
colours = 'Paired'
kwargs['colormap'] = colours
#else:
#if len(dataframe.T.columns) < 8:
#try:
#del kwargs['colormap']
#except:
#pass
# multicoloured bar charts
if 'kind' in kwargs:
if colours:
if kwargs['kind'].startswith('bar'):
if len(list(dataframe.columns)) == 1:
if not black_and_white:
import numpy as np
the_range = np.linspace(0, 1, num_to_plot)
cmap = plt.get_cmap(colours)
kwargs['colors'] = [cmap(n) for n in the_range]
# make a bar width ... ?
#kwargs['width'] = (figsize[0] / float(num_to_plot)) / 1.5
# reversing legend option
if reverse_legend is True:
rev_leg = True
elif reverse_legend is False:
rev_leg = False
# show legend or don't, guess whether to reverse based on kind
if 'kind' in kwargs:
if kwargs['kind'] in ['bar', 'barh', 'area', 'line', 'pie']:
if was_series:
legend = False
if kwargs['kind'] == 'pie':
if pie_legend:
legend = True
else:
legend = False
if kwargs['kind'] in ['barh', 'area']:
if reverse_legend == 'guess':
rev_leg = True
if not 'rev_leg' in locals():
rev_leg = False
# the default legend placement
if legend_pos is True:
legend_pos = 'best'
# cut dataframe if just_totals
try:
tst = dataframe['Combined total']
dataframe = dataframe.head(num_to_plot)
except:
pass
# rotate automatically
if 'rot' not in kwargs:
if not was_series:
xvals = [str(i) for i in list(dataframe.index)[:num_to_plot]]
#if 'kind' in kwargs:
#if kwargs['kind'] in ['barh', 'area']:
#xvals = [str(i) for i in list(dataframe.columns)[:num_to_plot]]
else:
xvals = [str(i) for i in list(dataframe.columns)[:num_to_plot]]
if len(max(xvals, key=len)) > 6:
if not piemode:
kwargs['rot'] = 45
# no title for subplots because ugly,
if sbplt:
if 'title' in kwargs:
del kwargs['title']
else:
kwargs['title'] = title
# no interactive subplots yet:
if sbplt and interactive:
import warnings
interactive = False
warnings.warn('No interactive subplots yet, sorry.')
return
# not using pandas for labels or legend anymore.
#kwargs['labels'] = None
#kwargs['legend'] = False
if legend:
# kwarg options go in leg_options
leg_options = {'framealpha': .8}
if 'shadow' in kwargs:
leg_options['shadow'] = True
if 'ncol' in kwargs:
leg_options['ncol'] = kwargs['ncol']
del kwargs['ncol']
else:
if num_to_plot > 6:
leg_options['ncol'] = num_to_plot / 7
# determine legend position based on this dict
if legend_pos:
possible = {'best': 0, 'upper right': 1, 'upper left': 2, 'lower left': 3, 'lower right': 4,
'right': 5, 'center left': 6, 'center right': 7, 'lower center': 8, 'upper center': 9,
'center': 10, 'o r': 2, 'outside right': 2, 'outside upper right': 2,
'outside center right': 'center left', 'outside lower right': 'lower left'}
if type(legend_pos) == int:
the_loc = legend_pos
elif type(legend_pos) == str:
try:
the_loc = possible[legend_pos]
except KeyError:
raise KeyError('legend_pos value must be one of:\n%s\n or an int between 0-10.' %', '.join(possible.keys()))
leg_options['loc'] = the_loc
#weirdness needed for outside plot
if legend_pos in ['o r', 'outside right', 'outside upper right']:
leg_options['bbox_to_anchor'] = (1.02, 1)
if legend_pos == 'outside center right':
leg_options['bbox_to_anchor'] = (1.02, 0.5)
if legend_pos == 'outside lower right':
leg_options['loc'] == 'upper right'
leg_options['bbox_to_anchor'] = (0.5, 0.5)
# a bit of distance between legend and plot for outside legends
if type(legend_pos) == str:
if legend_pos.startswith('o'):
leg_options['borderaxespad'] = 1
if not piemode:
if show_totals.endswith('both') or show_totals.endswith('legend'):
dataframe = rename_data_with_total(dataframe,
was_series = was_series,
using_tex = using_tex,
absolutes = absolutes)
else:
if pie_legend:
if show_totals.endswith('both') or show_totals.endswith('legend'):
dataframe = rename_data_with_total(dataframe,
was_series = was_series,
using_tex = using_tex,
absolutes = absolutes)
if piemode:
if partial_pie:
dataframe = dataframe / 100.0
# some pie things
if piemode:
if not sbplt:
kwargs['y'] = list(dataframe.columns)[0]
if pie_legend:
kwargs['legend'] = False
if was_series:
leg_options['labels'] = list(dataframe.index)
else:
leg_options['labels'] = list(dataframe.columns)
else:
if pie_legend:
kwargs['legend'] = False
if was_series:
leg_options['labels'] = list(dataframe.index)
else:
leg_options['labels'] = list(dataframe.index)
areamode = False
if 'kind' in kwargs:
if kwargs['kind'] == 'area':
areamode = True
if legend is False:
kwargs['legend'] = False
# cumulative grab first col
if cumulative:
kwargs['y'] = list(dataframe.columns)[0]
# line highlighting option for interactive!
if interactive:
if 2 in interactive_types:
if kwargs['kind'] == 'line':
kwargs['marker'] = ','
if not piemode:
kwargs['alpha'] = 0.1
# convert dates --- works only in my current case!
if plotting_a_totals_column or not was_series:
try:
can_it_be_int = int(list(dataframe.index)[0])
can_be_int = True
except:
can_be_int = False
if can_be_int:
if 1500 < int(list(dataframe.index)[0]):
if 2050 > int(list(dataframe.index)[0]):
n = pd.PeriodIndex([d for d in list(dataframe.index)], freq='A')
dataframe = dataframe.set_index(n)
MARKERSIZE = 4
COLORMAP = {
0: {'marker': None, 'dash': (None,None)},
1: {'marker': None, 'dash': [5,5]},
2: {'marker': "o", 'dash': (None,None)},
3: {'marker': None, 'dash': [1,3]},
4: {'marker': "s", 'dash': [5,2,5,2,5,10]},
5: {'marker': None, 'dash': [5,3,1,2,1,10]},
6: {'marker': 'o', 'dash': (None,None)},
7: {'marker': None, 'dash': [5,3,1,3]},
8: {'marker': "1", 'dash': [1,3]},
9: {'marker': "*", 'dash': [5,5]},
10: {'marker': "2", 'dash': [5,2,5,2,5,10]},
11: {'marker': "s", 'dash': (None,None)}
}
HATCHES = {
0: {'color': '#dfdfdf', 'hatch':"/"},
1: {'color': '#6f6f6f', 'hatch':"\\"},
2: {'color': 'b', 'hatch':"|"},
3: {'color': '#dfdfdf', 'hatch':"-"},
4: {'color': '#6f6f6f', 'hatch':"+"},
5: {'color': 'b', 'hatch':"x"}
}
if black_and_white:
if kwargs['kind'] == 'line':
kwargs['linewidth'] = 1
cmap = plt.get_cmap('Greys')
new_cmap = truncate_colormap(cmap, 0.25, 0.95)
if kwargs['kind'] == 'bar':
# darker if just one entry
if len(dataframe.columns) == 1:
new_cmap = truncate_colormap(cmap, 0.70, 0.90)
kwargs['colormap'] = new_cmap
# use styles and plot
with plt.style.context((style)):
if not sbplt:
# check if negative values, no stacked if so
if areamode:
if dataframe.applymap(lambda x: x < 0.0).any().any():
kwargs['stacked'] = False
rev_leg = False
ax = dataframe.plot(figsize = figsize, **kwargs)
else:
if not piemode and not sbplt:
ax = dataframe.plot(figsize = figsize, **kwargs)
else:
ax = dataframe.plot(figsize = figsize, **kwargs)
handles, labels = plt.gca().get_legend_handles_labels()
plt.legend( handles, labels, loc = leg_options['loc'], bbox_to_anchor = (0,-0.1,1,1),
bbox_transform = plt.gcf().transFigure )
if not tk:
plt.show()
return
if 'rot' in kwargs:
if kwargs['rot'] != 0 and kwargs['rot'] != 90:
labels = [item.get_text() for item in ax.get_xticklabels()]
ax.set_xticklabels(labels, rotation = kwargs['rot'], ha='right')
if transparent:
plt.gcf().patch.set_facecolor('white')
plt.gcf().patch.set_alpha(0)
if black_and_white:
#plt.grid()
plt.gca().set_axis_bgcolor('w')
if kwargs['kind'] == 'line':
# white background
# change everything to black and white with interesting dashes and markers
c = 0
for line in ax.get_lines():
line.set_color('black')
#line.set_width(1)
line.set_dashes(COLORMAP[c]['dash'])
line.set_marker(COLORMAP[c]['marker'])
line.set_markersize(MARKERSIZE)
c += 1
if c == len(COLORMAP.keys()):
c = 0
if legend:
if not piemode and not sbplt:
if 3 not in interactive_types:
if not rev_leg:
lgd = plt.legend(**leg_options)
else:
handles, labels = plt.gca().get_legend_handles_labels()
lgd = plt.legend(handles[::-1], labels[::-1], **leg_options)
#if black_and_white:
#lgd.set_facecolor('w')
#if interactive:
#if legend:
#lgd.set_title("")
#if not sbplt:
#if 'layout' not in kwargs:
#plt.tight_layout()
if interactive:
# 1 = highlight lines
# 2 = line labels
# 3 = legend switches
ax = plt.gca()
# fails for piemode
lines = ax.lines
handles, labels = plt.gca().get_legend_handles_labels()
if 1 in interactive_types:
plugins.connect(plt.gcf(), HighlightLines(lines))
if 3 in interactive_types:
plugins.connect(plt.gcf(), InteractiveLegendPlugin(lines, labels, alpha_unsel=0.0))
for i, l in enumerate(lines):
y_vals = l.get_ydata()
x_vals = l.get_xdata()
x_vals = [str(x) for x in x_vals]
if absolutes:
ls = ['%s (%s: %d)' % (labels[i], x_val, y_val) for x_val, y_val in zip(x_vals, y_vals)]
else:
ls = ['%s (%s: %.2f%%)' % (labels[i], x_val, y_val) for x_val, y_val in zip(x_vals, y_vals)]
if 2 in interactive_types:
#if 'kind' in kwargs and kwargs['kind'] == 'area':
tooltip_line = mpld3.plugins.LineLabelTooltip(lines[i], labels[i])
mpld3.plugins.connect(plt.gcf(), tooltip_line)
#else:
if kwargs['kind'] == 'line':
tooltip_point = mpld3.plugins.PointLabelTooltip(l, labels = ls)
mpld3.plugins.connect(plt.gcf(), tooltip_point)
# works:
#plugins.connect(plt.gcf(), plugins.LineLabelTooltip(l, labels[i]))
#labels = ["Point {0}".format(i) for i in range(num_to_plot)]
#tooltip = plugins.LineLabelTooltip(lines)
#mpld3.plugins.connect(plt.gcf(), mpld3.plugins.PointLabelTooltip(lines))
if piemode:
if not sbplt:
plt.axis('equal')
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
# add x label
# this could be revised now!
# if time series period, it's year for now
if type(dataframe.index) == pandas.tseries.period.PeriodIndex:
x_label = 'Year'
if x_label is not False:
if type(x_label) == str:
plt.xlabel(x_label)
else:
check_x_axis = list(dataframe.index)[0] # get first entry# get second entry of first entry (year, count)
try:
if type(dataframe.index) == pandas.tseries.period.PeriodIndex:
x_label = 'Year'
check_x_axis = int(check_x_axis)
if 1500 < check_x_axis < 2050:
x_label = 'Year'
else:
x_label = 'Group'
except:
x_label = 'Group'
if not sbplt:
if not piemode:
plt.xlabel(x_label)
# no offsets for numerical x and y values
if type(dataframe.index) != pandas.tseries.period.PeriodIndex:
try:
# check if x axis can be an int
check_x_axis = list(dataframe.index)[0]
can_it_be_int = int(check_x_axis)
# if so, set these things
from matplotlib.ticker import ScalarFormatter
plt.gca().xaxis.set_major_formatter(ScalarFormatter())
except:
pass
# same for y axis
try:
# check if x axis can be an int
check_y_axis = list(dataframe.columns)[0]
can_it_be_int = int(check_y_axis)
# if so, set these things
from matplotlib.ticker import ScalarFormatter
plt.gca().yaxis.set_major_formatter(ScalarFormatter())
except:
pass
# y labelling
y_l = False
if not absolutes:
y_l = 'Percentage'
else:
y_l = 'Absolute frequency'
if y_label is not False:
if not sbplt:
if not piemode:
if type(y_label) == str:
plt.ylabel(y_label)
else:
plt.ylabel(y_l)
# hacky: turn legend into subplot titles :)
if sbplt:
# title the big plot
#plt.suptitle(title, fontsize = 16)
# get all axes
if 'layout' not in kwargs:
axes = [l for index, l in enumerate(ax)]
else:
axes = []
cols = [l for index, l in enumerate(ax)]
for col in cols:
for bit in col:
axes.append(bit)
# set subplot titles
for index, a in enumerate(axes):
try:
titletext = list(dataframe.columns)[index]
except:
pass
a.set_title(titletext)
try:
a.legend_.remove()
except:
pass
# remove axis labels for pie plots
if piemode:
a.axes.get_xaxis().set_visible(False)
a.axes.get_yaxis().set_visible(False)
a.axis('equal')
# add sums to bar graphs and pie graphs
# doubled right now, no matter
if not sbplt:
if 'kind' in kwargs:
if kwargs['kind'].startswith('bar'):
width = ax.containers[0][0].get_width()
if was_series:
the_y_limit = plt.ylim()[1]
if show_totals.endswith('plot') or show_totals.endswith('both'):
# make plot a bit higher if putting these totals on it
plt.ylim([0,the_y_limit * 1.05])
for i, label in enumerate(list(dataframe.index)):
if len(dataframe.ix[label]) == 1:
score = dataframe.ix[label][0]
else:
if absolutes:
score = dataframe.ix[label].sum()
else:
#import warnings
#warnings.warn("It's not possible to determine total percentage from individual percentages.")
continue
if not absolutes:
plt.annotate('%.2f' % score, (i, score), ha = 'center', va = 'bottom')
else:
plt.annotate(score, (i, score), ha = 'center', va = 'bottom')
else:
the_y_limit = plt.ylim()[1]
if show_totals.endswith('plot') or show_totals.endswith('both'):
for i, label in enumerate(list(dataframe.columns)):
if len(dataframe[label]) == 1:
score = dataframe[label][0]
else:
if absolutes:
score = dataframe[label].sum()
else:
#import warnings
#warnings.warn("It's not possible to determine total percentage from individual percentages.")
continue
if not absolutes:
plt.annotate('%.2f' % score, (i, score), ha = 'center', va = 'bottom')
else:
plt.annotate(score, (i, score), ha = 'center', va = 'bottom')
#if not running_python_tex:
#plt.gcf().show()
plt.subplots_adjust(left=0.1)
plt.subplots_adjust(bottom=0.18)
#if 'layout' not in kwargs:
#plt.tight_layout()
if save:
import os
if running_python_tex:
imagefolder = '../images'
else:
imagefolder = 'images'
savename = get_savename(imagefolder, save = save, title = title, ext = output_format)
if not os.path.isdir(imagefolder):
os.makedirs(imagefolder)
# save image and get on with our lives
if legend_pos.startswith('o'):
plt.gcf().savefig(savename, dpi=150, bbox_extra_artists=(lgd,), bbox_inches='tight', format = output_format)
else:
plt.gcf().savefig(savename, dpi=150, format = output_format)
time = strftime("%H:%M:%S", localtime())
if os.path.isfile(savename):
print '\n' + time + ": " + savename + " created."
else:
raise ValueError("Error making %s." % savename)
if not interactive and not running_python_tex and not running_spider and not tk:
plt.show()
return
if running_spider or tk or sbplt:
return plt
if interactive:
plt.subplots_adjust(right=.8)
plt.subplots_adjust(left=.1)
try:
ax.legend_.remove()
except:
pass
return mpld3.display()
def plotter(title,
df,
kind = 'line',
x_label = None,
y_label = None,
style = 'ggplot',
figsize = (8, 4),
save = False,
legend_pos = 'best',
reverse_legend = 'guess',
num_to_plot = 7,
tex = 'try',
colours = 'Accent',
cumulative = False,
pie_legend = True,
partial_pie = False,
show_totals = False,
transparent = False,
output_format = 'png',
interactive = False,
black_and_white = False,
show_p_val = False,
indices = False,
**kwargs):
"""Visualise corpus interrogations.
:param title: A title for the plot
:type title: str
:param df: Data to be plotted
:type df: pandas.core.frame.DataFrame
:param x_label: A label for the x axis
:type x_label: str
:param y_label: A label for the y axis
:type y_label: str
:param kind: The kind of chart to make
:type kind: str ('line'/'bar'/'barh'/'pie'/'area')
:param style: Visual theme of plot
:type style: str ('ggplot'/'bmh'/'fivethirtyeight'/'seaborn-talk'/etc)
:param figsize: Size of plot
:type figsize: tuple (int, int)
:param save: If bool, save with *title* as name; if str, use str as name
:type save: bool/str
:param legend_pos: Where to place legend
:type legend_pos: str ('upper right'/'outside right'/etc)
:param reverse_legend: Reverse the order of the legend
:type reverse_legend: bool
:param num_to_plot: How many columns to plot
:type num_to_plot: int/'all'
:param tex: Use TeX to draw plot text
:type tex: bool
:param colours: Colourmap for lines/bars/slices
:type colours: str
:param cumulative: Plot values cumulatively
:type cumulative: bool
:param pie_legend: Show a legend for pie chart
:type pie_legend: bool
:param partial_pie: Allow plotting of pie slices only
:type partial_pie: bool
:param show_totals: Print sums in plot where possible
:type show_totals: str -- 'legend'/'plot'/'both'
:param transparent: Transparent .png background
:type transparent: bool
:param output_format: File format for saved image
:type output_format: str -- 'png'/'pdf'
:param black_and_white: Create black and white line styles
:type black_and_white: bool
:param show_p_val: Attempt to print p values in legend if contained in df
:type show_p_val: bool
:param indices: To use when plotting "distance from root"
:type indices: bool
:param stacked: When making bar chart, stack bars on top of one another
:type stacked: str
:param filled: For area and bar charts, make every column sum to 100
:type filled: str
:param legend: Show a legend
:type legend: bool
:param rot: Rotate x axis ticks by *rot* degrees
:type rot: int
:param subplots: Plot each column separately
:type subplots: bool
:param layout: Grid shape to use when *subplots* is True
:type layout: tuple -- (int, int)
:param interactive: Experimental interactive options
:type interactive: list -- [1, 2, 3]
:returns: matplotlib figure
"""
import corpkit
import os
try:
from IPython.utils.shimmodule import ShimWarning
import warnings
warnings.simplefilter('ignore', ShimWarning)
except:
pass
import matplotlib as mpl
from matplotlib import rc
# prefer seaborn plotting
try:
import seaborn as sns
except:
pass
if interactive:
import matplotlib.pyplot as plt, mpld3
else:
import matplotlib.pyplot as plt
import pandas
from pandas import DataFrame
import numpy
from time import localtime, strftime
from tests import check_pytex, check_spider, check_t_kinter
if interactive:
import mpld3
import collections
from mpld3 import plugins, utils
from plugins import InteractiveLegendPlugin, HighlightLines
# check what environment we're in
tk = check_t_kinter()
running_python_tex = check_pytex()
running_spider = check_spider()
def truncate_colormap(cmap, minval=0.0, maxval=1.0, n=100):
"""remove extreme values from colourmap --- no pure white"""
import matplotlib.colors as colors
import numpy as np
new_cmap = colors.LinearSegmentedColormap.from_list(
'trunc({n},{a:.2f},{b:.2f})'.format(n=cmap.name, a=minval, b=maxval),
cmap(np.linspace(minval, maxval, n)))
return new_cmap
def get_savename(imagefolder, save = False, title = False, ext = 'png'):
"""Come up with the savename for the image."""
import os
def urlify(s):
"Turn title into filename"
import re
s = s.lower()
s = re.sub(r"[^\w\s-]", '', s)
s = re.sub(r"\s+", '-', s)
s = re.sub(r"-(textbf|emph|textsc|textit)", '-', s)
return s
# name as
if not ext.startswith('.'):
ext = '.' + ext
if type(save) == str:
savename = os.path.join(imagefolder, (urlify(save) + ext))
#this 'else' is redundant now that title is obligatory
else:
if title:
filename = urlify(title) + ext
savename = os.path.join(imagefolder, filename)
# remove duplicated ext
if savename.endswith('%s%s' % (ext, ext)):
savename = savename.replace('%s%s' % (ext, ext), ext, 1)
return savename
def rename_data_with_total(dataframe, was_series = False, using_tex = False, absolutes = True):
"""adds totals (abs, rel, keyness) to entry name strings"""
if was_series:
where_the_words_are = dataframe.index
else:
where_the_words_are = dataframe.columns
the_labs = []
for w in list(where_the_words_are):
if not absolutes:
if was_series:
perc = dataframe.T[w][0]
else:
the_labs.append(w)
continue
if using_tex:
the_labs.append('%s (%.2f\%%)' % (w, perc))
else:
the_labs.append('%s (%.2f %%)' % (w, perc))
else:
if was_series:
score = dataframe.T[w].sum()
else:
score = dataframe[w].sum()
if using_tex:
the_labs.append('%s (n=%d)' % (w, score))
else:
the_labs.append('%s (n=%d)' % (w, score))
if not was_series:
dataframe.columns = the_labs
else:
vals = list(dataframe[list(dataframe.columns)[0]].values)
dataframe = pandas.DataFrame(vals, index = the_labs)
dataframe.columns = ['Total']
return dataframe
def auto_explode(dataframe, input, was_series = False, num_to_plot = 7):
"""give me a list of strings and i'll output explode option"""
output = [0 for s in range(num_to_plot)]
if was_series:
l = list(dataframe.index)
else:
l = list(dataframe.columns)
if type(input) == str or type(input) == int:
input = [input]
if type(input) == list:
for i in input:
if type(i) == str:
index = l.index(i)
else:
index = i
output[index] = 0.1
return output
# check if we're doing subplots
sbplt = False
if 'subplots' in kwargs:
if kwargs['subplots'] is True:
sbplt = True
kwargs['subplots'] = sbplt
if colours is True:
colours = 'Paired'
# todo: get this dynamically instead.
styles = ['dark_background', 'bmh', 'grayscale', 'ggplot', 'fivethirtyeight', 'matplotlib', False, 'mpl-white']
#if style not in styles:
#raise ValueError('Style %s not found. Use %s' % (str(style), ', '.join(styles)))
if style == 'mpl-white':
try:
sns.set_style("whitegrid")
except:
pass
style = 'matplotlib'
if style is not False and style.startswith('seaborn'):
colours = False
# use 'draggable = True' to make a draggable legend
dragmode = kwargs.get('draggable', False)
kwargs.pop('draggable', None)
if kwargs.get('savepath'):
mpl.rcParams['savefig.directory'] = kwargs.get('savepath')
kwargs.pop('savepath', None)
mpl.rcParams['savefig.bbox'] = 'tight'
mpl.rcParams.update({'figure.autolayout': True})
# try to use tex
# TO DO:
# make some font kwargs here
using_tex = False
mpl.rcParams['font.family'] = 'sans-serif'
mpl.rcParams['text.latex.unicode'] = True
if tex == 'try' or tex is True:
try:
rc('text', usetex=True)
rc('font', **{'family': 'serif', 'serif': ['Computer Modern']})
using_tex = True
except:
matplotlib.rc('font', family='sans-serif')
matplotlib.rc('font', serif='Helvetica Neue')
matplotlib.rc('text', usetex='false')
rc('text', usetex=False)
else:
rc('text', usetex=False)
if interactive:
using_tex = False
if show_totals is False:
show_totals = 'none'
# find out what kind of plot we're making, and enable
# or disable interactive values if need be
kwargs['kind'] = kind.lower()
if interactive:
if kwargs['kind'].startswith('bar'):
interactive_types = [3]
elif kwargs['kind'] == 'area':
interactive_types = [2, 3]
elif kwargs['kind'] == 'line':
interactive_types = [2, 3]
elif kwargs['kind'] == 'pie':
interactive_types = None
warnings.warn('Interactive plotting not yet available for pie plots.')
else:
interactive_types = [None]
if interactive is False:
interactive_types = [None]
# find out if pie mode, add autopct format
piemode = False
if kind == 'pie':
piemode = True
# always the best spot for pie
#if legend_pos == 'best':
#legend_pos = 'lower left'
if show_totals.endswith('plot') or show_totals.endswith('both'):
kwargs['pctdistance'] = 0.6
if using_tex:
kwargs['autopct'] = r'%1.1f\%%'
else:
kwargs['autopct'] = '%1.1f%%'
# copy data, make series into df
dataframe = df.copy()
was_series = False
if type(dataframe) == pandas.core.series.Series:
was_series = True
if not cumulative:
dataframe = DataFrame(dataframe)
else:
dataframe = DataFrame(dataframe.cumsum())
else:
# don't know if this is much good.
if cumulative:
dataframe = DataFrame(dataframe.cumsum())
if len(list(dataframe.columns)) == 1:
was_series = True
# attempt to convert x axis to ints:
try:
dataframe.index = [int(i) for i in list(dataframe.index)]
except:
pass
# remove totals and tkinter order
if not was_series and not all(x.lower() == 'total' for x in list(dataframe.columns)):
for name, ax in zip(['Total'] * 2 + ['tkintertable-order'] * 2, [0, 1, 0, 1]):
try:
dataframe = dataframe.drop(name, axis = ax, errors = 'ignore')
except:
pass
else:
dataframe = dataframe.drop('tkintertable-order', errors = 'ignore')
dataframe = dataframe.drop('tkintertable-order', axis = 1, errors = 'ignore')
# look at columns to see if all can be ints, in which case, set up figure
# for depnumming
if not was_series:
if indices == 'guess':
def isint(x):
try:
a = float(x)
b = int(a)
except ValueError or OverflowError:
return False
else:
return a == b
if all([isint(x) is True for x in list(dataframe.columns)]):
indices = True
else:
indices = False
# if depnumming, plot all, transpose, and rename axes
if indices is True:
num_to_plot = 'all'
dataframe = dataframe.T
if y_label is None:
y_label = 'Percentage of all matches'
if x_label is None:
x_label = ''
# set backend?
output_formats = ['svgz', 'ps', 'emf', 'rgba', 'raw', 'pdf', 'svg', 'eps', 'png', 'pgf']
if output_format not in output_formats:
raise ValueError('%s output format not recognised. Must be: %s' % (output_format, ', '.join(output_formats)))
# don't know if these are necessary
if 'pdf' in output_format:
plt.switch_backend(output_format)
if 'pgf' in output_format:
plt.switch_backend(output_format)
if num_to_plot == 'all':
if was_series:
if not piemode:
num_to_plot = len(dataframe)
else:
num_to_plot = len(dataframe)
else:
if not piemode:
num_to_plot = len(list(dataframe.columns))
else:
num_to_plot = len(dataframe.index)
# explode pie, or remove if not piemode
if piemode and not sbplt and kwargs.get('explode'):
kwargs['explode'] = auto_explode(dataframe,
kwargs['explode'],
was_series = was_series,
num_to_plot = num_to_plot)
else:
kwargs.pop('explode', None)
legend = kwargs.get('legend', False)
#cut data short
plotting_a_totals_column = False
if was_series:
if list(dataframe.columns)[0] != 'Total':
try:
can_be_ints = [int(x) for x in list(dataframe.index)]
num_to_plot = len(dataframe)
except:
dataframe = dataframe[:num_to_plot]
elif list(dataframe.columns)[0] == 'Total':
plotting_a_totals_column = True
if not 'legend' in kwargs:
legend = False
num_to_plot = len(dataframe)
else:
dataframe = dataframe.T.head(num_to_plot).T
# remove stats fields, put p in entry text, etc.
statfields = ['slope', 'intercept', 'r', 'p', 'stderr']
try:
dataframe = dataframe.drop(statfields, axis = 1, errors = 'ignore')
except:
pass
try:
dataframe.ix['p']
there_are_p_vals = True
except:
there_are_p_vals = False
if show_p_val:
if there_are_p_vals:
newnames = []
for col in list(dataframe.columns):
pval = dataframe[col]['p']
def p_string_formatter(val):
if val < 0.001:
if not using_tex:
return 'p < 0.001'
else:
return r'p $<$ 0.001'
else:
return 'p = %s' % format(val, '.3f')
pstr = p_string_formatter(pval)
newname = '%s (%s)' % (col, pstr)
newnames.append(newname)
dataframe.columns = newnames
dataframe.drop(statfields, axis = 0, inplace = True, errors = 'ignore')
else:
warnings.warn('No p-values calculated to show.\n\nUse sort_by and keep_stats in editor() to generate these values.')
else:
if there_are_p_vals:
dataframe.drop(statfields, axis = 0, inplace = True, errors = 'ignore')
# make and set y label
absolutes = True
if type(dataframe) == pandas.core.frame.DataFrame:
try:
if not all([s.is_integer() for s in dataframe.iloc[0,:].values]):
absolutes = False
except:
pass
else:
if not all([s.is_integer() for s in dataframe.values]):
absolutes = False
# use colormap if need be:
if num_to_plot > 0:
if not was_series:
if kind in ['pie', 'line', 'area']:
if colours:
if not plotting_a_totals_column:
if colours == 'Default':
colours = 'Paired'
kwargs['colormap'] = colours
#else:
if colours:
if colours == 'Default':
colours = 'Paired'
kwargs['colormap'] = colours
if piemode:
if num_to_plot > 0:
if colours == 'Default':
colours = 'Paired'
kwargs['colormap'] = colours
else:
if num_to_plot > 0:
if colours == 'Default':
colours = 'Paired'
kwargs['colormap'] = colours
# multicoloured bar charts
if colours:
if kind.startswith('bar'):
if len(list(dataframe.columns)) == 1:
if not black_and_white:
import numpy as np
the_range = np.linspace(0, 1, num_to_plot)
cmap = plt.get_cmap(colours)
kwargs['colors'] = [cmap(n) for n in the_range]
# make a bar width ... ? ...
#kwargs['width'] = (figsize[0] / float(num_to_plot)) / 1.5
# reversing legend option
if reverse_legend is True:
rev_leg = True
elif reverse_legend is False:
rev_leg = False
# show legend or don't, guess whether to reverse based on kind
if kind in ['bar', 'barh', 'area', 'line', 'pie']:
if was_series:
legend = False
if kind == 'pie':
if pie_legend:
legend = True
else:
legend = False
if kind in ['barh', 'area']:
if reverse_legend == 'guess':
rev_leg = True
if not 'rev_leg' in locals():
rev_leg = False
# the default legend placement
if legend_pos is True:
legend_pos = 'best'
# cut dataframe if just_totals
try:
tst = dataframe['Combined total']
dataframe = dataframe.head(num_to_plot)
except:
pass
# rotate automatically
if 'rot' not in kwargs:
if not was_series:
xvals = [str(i) for i in list(dataframe.index)[:num_to_plot]]
#if 'kind' in kwargs:
#if kwargs['kind'] in ['barh', 'area']:
#xvals = [str(i) for i in list(dataframe.columns)[:num_to_plot]]
else:
xvals = [str(i) for i in list(dataframe.columns)[:num_to_plot]]
if len(max(xvals, key=len)) > 6:
if not piemode:
kwargs['rot'] = 45
# no title for subplots because ugly,
if title and not sbplt:
kwargs['title'] = title
# no interactive subplots yet:
if sbplt and interactive:
import warnings
interactive = False
warnings.warn('No interactive subplots yet, sorry.')
return
# not using pandas for labels or legend anymore.
#kwargs['labels'] = None
#kwargs['legend'] = False
if legend:
if num_to_plot > 6:
if not kwargs.get('ncol'):
kwargs['ncol'] = num_to_plot / 7
# kwarg options go in leg_options
leg_options = {'framealpha': .8,
'shadow': kwargs.get('shadow', False),
'ncol': kwargs.pop('ncol', 1)}
# determine legend position based on this dict
if legend_pos:
possible = {'best': 0, 'upper right': 1, 'upper left': 2, 'lower left': 3, 'lower right': 4,
'right': 5, 'center left': 6, 'center right': 7, 'lower center': 8, 'upper center': 9,
'center': 10, 'o r': 2, 'outside right': 2, 'outside upper right': 2,
'outside center right': 'center left', 'outside lower right': 'lower left'}
if type(legend_pos) == int:
the_loc = legend_pos
elif type(legend_pos) == str:
try:
the_loc = possible[legend_pos]
except KeyError:
raise KeyError('legend_pos value must be one of:\n%s\n or an int between 0-10.' %', '.join(list(possible.keys())))
leg_options['loc'] = the_loc
#weirdness needed for outside plot
if legend_pos in ['o r', 'outside right', 'outside upper right']:
leg_options['bbox_to_anchor'] = (1.02, 1)
if legend_pos == 'outside center right':
leg_options['bbox_to_anchor'] = (1.02, 0.5)
if legend_pos == 'outside lower right':
leg_options['loc'] == 'upper right'
leg_options['bbox_to_anchor'] = (0.5, 0.5)
# a bit of distance between legend and plot for outside legends
if type(legend_pos) == str:
if legend_pos.startswith('o'):
leg_options['borderaxespad'] = 1
if not piemode:
if show_totals.endswith('both') or show_totals.endswith('legend'):
dataframe = rename_data_with_total(dataframe,
was_series = was_series,
using_tex = using_tex,
absolutes = absolutes)
else:
if pie_legend:
if show_totals.endswith('both') or show_totals.endswith('legend'):
dataframe = rename_data_with_total(dataframe,
was_series = was_series,
using_tex = using_tex,
absolutes = absolutes)
if piemode:
if partial_pie:
dataframe = dataframe / 100.0
# some pie things
if piemode:
if not sbplt:
kwargs['y'] = list(dataframe.columns)[0]
if pie_legend:
kwargs['legend'] = False
if was_series:
leg_options['labels'] = list(dataframe.index)
else:
leg_options['labels'] = list(dataframe.columns)
else:
if pie_legend:
kwargs['legend'] = False
if was_series:
leg_options['labels'] = list(dataframe.index)
else:
leg_options['labels'] = list(dataframe.index)
def filler(df):
pby = df.T.copy()
for i in list(pby.columns):
tot = pby[i].sum()
pby[i] = pby[i] * 100.0 / tot
return pby.T
areamode = False
if kind == 'area':
areamode = True
if legend is False:
kwargs['legend'] = False
# line highlighting option for interactive!
if interactive:
if 2 in interactive_types:
if kind == 'line':
kwargs['marker'] = ','
if not piemode:
kwargs['alpha'] = 0.1
# convert dates --- works only in my current case!
if plotting_a_totals_column or not was_series:
try:
can_it_be_int = int(list(dataframe.index)[0])
can_be_int = True
except:
can_be_int = False
if can_be_int:
if 1500 < int(list(dataframe.index)[0]):
if 2050 > int(list(dataframe.index)[0]):
n = pandas.PeriodIndex([d for d in list(dataframe.index)], freq='A')
dataframe = dataframe.set_index(n)
if kwargs.get('filled'):
if areamode or kind.startswith('bar'):
dataframe = filler(dataframe)
kwargs.pop('filled', None)
MARKERSIZE = 4
COLORMAP = {
0: {'marker': None, 'dash': (None,None)},
1: {'marker': None, 'dash': [5,5]},
2: {'marker': "o", 'dash': (None,None)},
3: {'marker': None, 'dash': [1,3]},
4: {'marker': "s", 'dash': [5,2,5,2,5,10]},
5: {'marker': None, 'dash': [5,3,1,2,1,10]},
6: {'marker': 'o', 'dash': (None,None)},
7: {'marker': None, 'dash': [5,3,1,3]},
8: {'marker': "1", 'dash': [1,3]},
9: {'marker': "*", 'dash': [5,5]},
10: {'marker': "2", 'dash': [5,2,5,2,5,10]},
11: {'marker': "s", 'dash': (None,None)}
}
HATCHES = {
0: {'color': '#dfdfdf', 'hatch':"/"},
1: {'color': '#6f6f6f', 'hatch':"\\"},
2: {'color': 'b', 'hatch':"|"},
3: {'color': '#dfdfdf', 'hatch':"-"},
4: {'color': '#6f6f6f', 'hatch':"+"},
5: {'color': 'b', 'hatch':"x"}
}
if black_and_white:
if kind == 'line':
kwargs['linewidth'] = 1
cmap = plt.get_cmap('Greys')
new_cmap = truncate_colormap(cmap, 0.25, 0.95)
if kind == 'bar':
# darker if just one entry
if len(dataframe.columns) == 1:
new_cmap = truncate_colormap(cmap, 0.70, 0.90)
kwargs['colormap'] = new_cmap
class dummy_context_mgr():
"""a fake context for plotting without style
perhaps made obsolete by 'classic' style in new mpl"""
def __enter__(self):
return None
def __exit__(self, one, two, three):
return False
with plt.style.context((style)) if style != 'matplotlib' else dummy_context_mgr():
if not sbplt:
# check if negative values, no stacked if so
if areamode:
kwargs['legend'] = False
if dataframe.applymap(lambda x: x < 0.0).any().any():
kwargs['stacked'] = False
rev_leg = False
ax = dataframe.plot(figsize = figsize, **kwargs)
if areamode:
handles, labels = plt.gca().get_legend_handles_labels()
del handles
del labels
else:
plt.gcf().set_tight_layout(False)
if not piemode:
ax = dataframe.plot(figsize = figsize, **kwargs)
else:
ax = dataframe.plot(figsize = figsize, **kwargs)
handles, labels = plt.gca().get_legend_handles_labels()
plt.legend( handles, labels, loc = leg_options['loc'], bbox_to_anchor = (0,-0.1,1,1),
bbox_transform = plt.gcf().transFigure )
# this line allows layouts with missing plots
# i.e. layout = (5, 2) with only nine plots
plt.gcf().set_tight_layout(False)
if 'rot' in kwargs:
if kwargs['rot'] != 0 and kwargs['rot'] != 90:
labels = [item.get_text() for item in ax.get_xticklabels()]
ax.set_xticklabels(labels, rotation = kwargs['rot'], ha='right')
if transparent:
plt.gcf().patch.set_facecolor('white')
plt.gcf().patch.set_alpha(0)
if black_and_white:
if kind == 'line':
# white background
# change everything to black and white with interesting dashes and markers
c = 0
for line in ax.get_lines():
line.set_color('black')
#line.set_width(1)
line.set_dashes(COLORMAP[c]['dash'])
line.set_marker(COLORMAP[c]['marker'])
line.set_markersize(MARKERSIZE)
c += 1
if c == len(list(COLORMAP.keys())):
c = 0
# draw legend with proper placement etc
if legend:
if not piemode and not sbplt:
if 3 not in interactive_types:
handles, labels = plt.gca().get_legend_handles_labels()
# area doubles the handles and labels. this removes half:
if areamode:
handles = handles[-len(handles) / 2:]
labels = labels[-len(labels) / 2:]
if rev_leg:
handles = handles[::-1]
labels = labels[::-1]
lgd = plt.legend(handles, labels, **leg_options)
if interactive:
# 1 = highlight lines
# 2 = line labels
# 3 = legend switches
ax = plt.gca()
# fails for piemode
lines = ax.lines
handles, labels = plt.gca().get_legend_handles_labels()
if 1 in interactive_types:
plugins.connect(plt.gcf(), HighlightLines(lines))
if 3 in interactive_types:
plugins.connect(plt.gcf(), InteractiveLegendPlugin(lines, labels, alpha_unsel=0.0))
for i, l in enumerate(lines):
y_vals = l.get_ydata()
x_vals = l.get_xdata()
x_vals = [str(x) for x in x_vals]
if absolutes:
ls = ['%s (%s: %d)' % (labels[i], x_val, y_val) for x_val, y_val in zip(x_vals, y_vals)]
else:
ls = ['%s (%s: %.2f%%)' % (labels[i], x_val, y_val) for x_val, y_val in zip(x_vals, y_vals)]
if 2 in interactive_types:
#if 'kind' in kwargs and kwargs['kind'] == 'area':
tooltip_line = mpld3.plugins.LineLabelTooltip(lines[i], labels[i])
mpld3.plugins.connect(plt.gcf(), tooltip_line)
#else:
if kind == 'line':
tooltip_point = mpld3.plugins.PointLabelTooltip(l, labels = ls)
mpld3.plugins.connect(plt.gcf(), tooltip_point)
if piemode:
if not sbplt:
plt.axis('equal')
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
# add x label
# this could be revised now!
# if time series period, it's year for now
if type(dataframe.index) == pandas.tseries.period.PeriodIndex:
x_label = 'Year'
if x_label is not False:
if type(x_label) == str:
plt.xlabel(x_label)
else:
check_x_axis = list(dataframe.index)[0] # get first entry# get second entry of first entry (year, count)
try:
if type(dataframe.index) == pandas.tseries.period.PeriodIndex:
x_label = 'Year'
check_x_axis = int(check_x_axis)
if 1500 < check_x_axis < 2050:
x_label = 'Year'
else:
x_label = 'Group'
except:
x_label = 'Group'
if not sbplt:
if not piemode:
plt.xlabel(x_label)
def is_number(s):
"""check if str can be can be made into float/int"""
try:
float(s) # for int, long and float
except ValueError:
try:
complex(s) # for complex
except ValueError:
return False
return True
# for now, always turn off sci notation
from matplotlib.ticker import ScalarFormatter
if type(dataframe.index) != pandas.tseries.period.PeriodIndex:
try:
if all(is_number(s) for s in list(dataframe.index)):
plt.gca().xaxis.set_major_formatter(ScalarFormatter())
except:
pass
try:
if all(is_number(s) for s in list(dataframe.columns)):
plt.gca().yaxis.set_major_formatter(ScalarFormatter())
except:
pass
# y labelling
y_l = False
if not absolutes:
y_l = 'Percentage'
else:
y_l = 'Absolute frequency'
def suplabel(axis,label,label_prop=None,
labelpad=5,
ha='center',va='center'):
''' Add super ylabel or xlabel to the figure
Similar to matplotlib.suptitle
axis - string: "x" or "y"
label - string
label_prop - keyword dictionary for Text
labelpad - padding from the axis (default: 5)
ha - horizontal alignment (default: "center")
va - vertical alignment (default: "center")
'''
fig = plt.gcf()
xmin = []
ymin = []
for ax in fig.axes:
xmin.append(ax.get_position().xmin)
ymin.append(ax.get_position().ymin)
xmin,ymin = min(xmin),min(ymin)
dpi = fig.dpi
if axis.lower() == "y":
rotation=90.
x = xmin-float(labelpad)/dpi
y = 0.5
elif axis.lower() == 'x':
rotation = 0.
x = 0.5
y = ymin - float(labelpad)/dpi
else:
raise Exception("Unexpected axis: x or y")
if label_prop is None:
label_prop = dict()
plt.gcf().text(x,y,label,rotation=rotation,
transform=fig.transFigure,
ha=ha,va=va,
**label_prop)
if y_label is not False:
if not sbplt:
if not piemode:
if type(y_label) == str:
plt.ylabel(y_label)
else:
plt.ylabel(y_l)
else:
if type(y_label) == str:
the_y = y_label
else:
the_y = y_l
#suplabel('y', the_y, labelpad = 1.5)
plt.gcf().text(0.04, 0.5, the_y, va='center', rotation='vertical')
#plt.subplots_adjust(left=0.5)
# if not piemode:
# if type(y_label) == str:
# plt.ylabel(y_label)
# else:
# plt.ylabel(y_l)
# hacky: turn legend into subplot titles :)
if sbplt:
# title the big plot
#plt.gca().suptitle(title, fontsize = 16)
#plt.subplots_adjust(top=0.9)
# get all axes
if 'layout' not in kwargs:
axes = [l for index, l in enumerate(ax)]
else:
axes = []
cols = [l for index, l in enumerate(ax)]
for col in cols:
for bit in col:
axes.append(bit)
# set subplot titles
for index, a in enumerate(axes):
try:
titletext = list(dataframe.columns)[index]
except:
pass
a.set_title(titletext)
try:
a.legend_.remove()
except:
pass
# remove axis labels for pie plots
if piemode:
a.axes.get_xaxis().set_visible(False)
a.axes.get_yaxis().set_visible(False)
a.axis('equal')
# show grid
a.grid(b=kwargs.get('grid', False))
kwargs.pop('grid', None)
# add sums to bar graphs and pie graphs
# doubled right now, no matter
if not sbplt:
if kind.startswith('bar'):
width = ax.containers[0][0].get_width()
# show grid
ax.grid(b=kwargs.get('grid', False))
kwargs.pop('grid', None)
if was_series:
the_y_limit = plt.ylim()[1]
if show_totals.endswith('plot') or show_totals.endswith('both'):
# make plot a bit higher if putting these totals on it
plt.ylim([0,the_y_limit * 1.05])
for i, label in enumerate(list(dataframe.index)):
if len(dataframe.ix[label]) == 1:
score = dataframe.ix[label][0]
else:
if absolutes:
score = dataframe.ix[label].sum()
else:
#import warnings
#warnings.warn("It's not possible to determine total percentage from individual percentages.")
continue
if not absolutes:
plt.annotate('%.2f' % score, (i, score), ha = 'center', va = 'bottom')
else:
plt.annotate(score, (i, score), ha = 'center', va = 'bottom')
else:
the_y_limit = plt.ylim()[1]
if show_totals.endswith('plot') or show_totals.endswith('both'):
for i, label in enumerate(list(dataframe.columns)):
if len(dataframe[label]) == 1:
score = dataframe[label][0]
else:
if absolutes:
score = dataframe[label].sum()
else:
#import warnings
#warnings.warn("It's not possible to determine total percentage from individual percentages.")
continue
if not absolutes:
plt.annotate('%.2f' % score, (i, score), ha = 'center', va = 'bottom')
else:
plt.annotate(score, (i, score), ha = 'center', va = 'bottom')
plt.subplots_adjust(left=0.1)
plt.subplots_adjust(bottom=0.18)
if 'layout' not in kwargs:
if not sbplt:
plt.tight_layout()
if save:
import os
if running_python_tex:
imagefolder = '../images'
else:
imagefolder = 'images'
savename = get_savename(imagefolder, save = save, title = title, ext = output_format)
if not os.path.isdir(imagefolder):
os.makedirs(imagefolder)
# save image and get on with our lives
if legend_pos.startswith('o'):
plt.gcf().savefig(savename, dpi=150, bbox_extra_artists=(lgd,), bbox_inches='tight', format = output_format)
else:
plt.gcf().savefig(savename, dpi=150, format = output_format)
time = strftime("%H:%M:%S", localtime())
if os.path.isfile(savename):
print('\n' + time + ": " + savename + " created.")
else:
raise ValueError("Error making %s." % savename)
if dragmode:
plt.legend().draggable()
if sbplt:
plt.subplots_adjust(right=.8)
plt.subplots_adjust(left=.1)
if not interactive and not running_python_tex and not running_spider \
and not tk:
plt.gcf().show()
return
elif running_spider or tk:
return plt
if interactive:
plt.subplots_adjust(right=.8)
plt.subplots_adjust(left=.1)
try:
ax.legend_.remove()
except:
pass
return mpld3.display()
def topic_sim(segrated_result):
#print segrated_result.info
texts_list = segrated_result.snippet2.tolist()
#print(texts_list)
vectorizer = TfidfVectorizer()
dtm = vectorizer.fit_transform(texts_list)
invtrm = vectorizer.inverse_transform(dtm)
#print invtrm
#print(invtrm)
vocab = vectorizer.get_feature_names()
#print(vectorizer.vocabulary_)
#print dtm.shape
scipy.sparse.csr.csr_matrix
dtm = dtm.toarray() # convert to a regular array
#print(dtm)
#vocab = np.array(vocab)
#print(vocab)
# for v in vocab:
# print(v)
dist = 1 - cosine_similarity(dtm)
np.round(dist, 2)
np.round(dist, 2).shape
# norms = np.sqrt(np.sum(dtm * dtm, axis=1, keepdims=True)) # multiplication between arrays is element-wise
# dtm_normed = dtm / norms
# similarities = np.dot(dtm_normed, dtm_normed.T)
# np.round(similarities, 2)
mds = MDS(n_components=2, dissimilarity="precomputed", random_state=1)
pos = mds.fit_transform(dist) # shape (n_components, n_samples)
#print dist
xs, ys = pos[:, 0], pos[:, 1]
names = list(reversed(range(1, len(xs), 1)))
# plt.style.use('fivethirtyeight')
# for x, y, name in zip(xs, ys, names):
# plt.title("Visualizing distances between the different text corpuses")
# plt.scatter(x, y)
# plt.text(x, y, name)
# #plt.show()
# fig, ax = plt.subplots()
# np.random.seed(0)
# color, size = np.random.random((2, len(xs)))
# for x, y, name in zip(xs, ys, names):
# # #ax.plot(np.random.normal(size=100),np.random.normal(size=100),'or', ms=10, alpha=0.3)
# # #ax.plot(np.random.normal(size=100),np.random.normal(size=100),'ob', ms=20, alpha=0.1)
# #
# ax.set_xlabel('x')
# ax.set_ylabel('y')
# ax.set_title('Visualizing distances between the different text corpuses', size=15)
# ax.grid(color='lightgray', alpha=0.7)
# # #ax.plot(x, y)
# #
# ax.scatter(x, y, c=color, s=500 * size, alpha=0.3)
# ax.text(x,y,name)
fig, ax = plt.subplots()
#N = 100
color, size = np.random.random((2, len(xs)))
scatter = ax.scatter(xs,
ys,
c=color,
s=1000 * size,
alpha=0.3,
cmap=plt.cm.jet)
ax.grid(color='lightgray', linestyle='solid', alpha=0.7)
ax.set_title('Scatter plot of text corpuses distances', size=16)
labels = ['Text {0}'.format(i) for i in names]
tooltip = mpld3.plugins.PointLabelTooltip(scatter, labels=labels)
mpld3.plugins.connect(fig, tooltip)
# # Scatter points
# fig, ax = plt.subplots()
# np.random.seed(0)
# #x, y = np.random.normal(size=(2, 200))
# color, size = np.random.random((2, len(xs)))
# print names
# ax.scatter(xs, ys, c=color, s=500 * size, alpha=0.3)
# #ax.text(xs,ys,names)
# ax.grid(color='lightgray', alpha=0.7)
tfidf_feature_names = vectorizer.get_feature_names()
no_topics = 20
# Run NMF
#nmf = NMF(n_components=no_topics, random_state=1, alpha=.1, l1_ratio=.5, init='nndsvd').fit(dtm)
# Run LDA
lda = LatentDirichletAllocation(n_topics=no_topics,
max_iter=500,
learning_method='online',
learning_offset=50.,
random_state=0).fit(dtm)
no_top_words = 10
#display_topics(nmf, tfidf_feature_names, no_top_words)
#display_topics(lda, tf_feature_names, no_top_words)
display_result = display_topics(lda, tfidf_feature_names, no_top_words)
#return mpld3.display(fig)
return display_result, mpld3.display()
column_rename_map = {'season': 'Season',
'number': 'Episode',
'rating' : 'Rating',
'votes' : 'Votes',
'first_aired' : 'Air date',
'overview' : 'Synopsis'}
for i in range(len(df)):
label = df.iloc[[i]][columns_for_labels].T
label.columns = df.iloc[[i]].title
labels.append(label.rename(column_rename_map).to_html())
# Plot scatter points
c = (df.season-1).map(pd.Series(list(sns.color_palette(n_colors=len(df.season.value_counts())))))
points = ax.scatter(df.number_abs, df.rating, alpha=.99, c=c, zorder=2)
ax.set_ylim(5,10)
ax.set_xlim(0,main_episodes.number_abs.max()+1)
ax.set_ylabel('Trakt.tv Episode Rating')
ax.set_xlabel('Episode number')
fig.set_size_inches(12, 6)
ax.set_title(show_summary.title[0], size=20)
tooltip = plugins.PointHTMLTooltip(points, labels,
voffset=10, hoffset=10, css=css)
plugins.connect(fig, tooltip)
mpld3.save_html(fig, str(show_summary.title[0] + ".html"))
mpld3.display()
import matplotlib.pyplot as plt
import numpy as np
import mpld3
from mpld3 import plugins
fig, ax = plt.subplots()
x = np.linspace(-2, 2, 20)
y = x[:, None]
X = np.zeros((20, 20, 4))
X[:, :, 0] = np.exp(- (x - 1) ** 2 - (y) ** 2)
X[:, :, 1] = np.exp(- (x + 0.71) ** 2 - (y - 0.71) ** 2)
X[:, :, 2] = np.exp(- (x + 0.71) ** 2 - (y + 0.71) ** 2)
X[:, :, 3] = np.exp(-0.25 * (x ** 2 + y ** 2))
im = ax.imshow(X, extent=(10, 20, 10, 20),
origin='lower', zorder=1, interpolation='nearest')
fig.colorbar(im, ax=ax)
ax.set_title('An Image', size=20)
plugins.connect(fig, plugins.MousePosition(fontsize=14))
mpld3.display(fig)
def make_figure(figANDax, sample_data):
fig, ax, fig2, ax2 = figANDax
with open('tp', 'rb') as f: # Python 3: open(..., 'rb')
hdist, tst_data = pickle.load(f)
hdist = np.array(hdist).reshape([512, 512])
col = []
# data=np.array([[]]);np.array()
tst_data = np.array(tst_data)
tst_data = tst_data
cm = plt.cm.rainbow
col = col + list(cm(.01) for i in range(tst_data.shape[0]))
sample_data = np.array(sample_data)
col += list(cm(.9) for i in range(sample_data.shape[0]))
data = np.vstack((tst_data, sample_data))
xs = data[:, 3]
xs = xs.astype(np.float)
xs[np.isnan(xs)] = 0
ys = (data[:, 4].astype(np.float))
# ys[ys==0]=1;
# ys=np.log(ys);
ys[~np.isfinite(ys)] = 0
zs = (data[:, 5].astype(np.float))
zs[~np.isfinite(zs)] = 0
sizs = list((.6 - float(x)) / .00755 for x in data[:, 5])
N = xs.size
labels = list(data[:, 1])
# labels=data[:,[0,1,3]].T.to_html
# fig, ax = plt.subplots(subplot_kw=dict(axisbg='#DDDDDD'
# ,projection='3d'
# ))
fig.set_size_inches([5, 4])
ax.grid(color='white', linestyle='solid')
ax.set_ylim(0, 0.38)
ax.set_xlim(0, 1)
put_patches(ax)
sct = ax.scatter(
xs,
ys,
c=col,
s=sizs,
alpha=1.0,
# label=labels,
cmap=plt.cm.rainbow)
red_patch = mpatches.Patch(color=plt.cm.rainbow(.98), label='The red data')
pur_patch = mpatches.Patch(color=plt.cm.rainbow(.02), label='The red data')
yel_patch = mpatches.Patch(color=plt.cm.rainbow(.02), label='The red data')
handles, leglabels = ax.get_legend_handles_labels()
handles += [red_patch, pur_patch]
leglabels += ['sample', 'reference']
ax.legend(handles, leglabels)
ax.set_title("Dynamic landscape, 2D projection", size=20)
plugins.connect(
fig,
plugins.PointLabelTooltip(sct, labels),
# plugins.Zoom(enabled=False),
ClickInfo(sct, labels))
ax.set_xlabel('Avg Temp', size=15)
ax.set_ylabel('mean(abs(d_Temp)) - abs(mean(d_Temp))', size=15)
sct3d = ax2.scatter(
xs,
ys,
zs,
c=col,
# c=list( 1.*float(i)/N for i in xs),
s=sizs,
alpha=1.0,
# label=labels,
cmap=plt.cm.rainbow)
ax2.set_title("Dynamic landscape, 3D", size=20)
ax2.set_xlabel('Avg Temp', size=15)
ax2.set_ylabel('mean(abs(d_Temp)) - abs(mean(d_Temp))', size=15)
ax2.set_zlabel('Density of dominating state', size=15)
mpld3.display(fig)
voffset=10, hoffset=10, css=css)
#connect tooltip to fig
mpld3.plugins.connect(fig, tooltip, TopToolbar())
#set tick marks as blank
ax.axes.get_xaxis().set_ticks([])
ax.axes.get_yaxis().set_ticks([])
#set axis as blank
ax.axes.get_xaxis().set_visible(False)
ax.axes.get_yaxis().set_visible(False)
ax.legend(numpoints=1) #show legend with only one dot
mpld3.display() #show the plot
#uncomment the below to export to html
#html = mpld3.fig_to_html(fig)
#print(html)
# # Hierarchical document clusterin
from scipy.cluster.hierarchy import ward, dendrogram
linkage_matrix = ward(dist) #define the linkage_matrix using ward clustering pre-computed distances
fig, ax = plt.subplots(figsize=(15, 20)) # set size
ax = dendrogram(linkage_matrix, orientation="right", labels=titles);
def mouseshow():
fig = gcf()
plugins.connect(fig, plugins.MousePosition(fontsize=14))
return mpld3.display(fig)
annot.set_visible(False)
fig.canvas.draw_idle()
fig.canvas.mpl_connect("motion_notify_event", hover)
plt.show()
#%% Matplot tooltips hack
import numpy as np
import matplotlib.pyplot as plt, mpld3
import seaborn as sns
import pandas as pd
N=10
data = pd.DataFrame({"x": np.random.randn(N),
"y": np.random.randn(N),
"size": np.random.randint(20,200, size=N),
"label": np.arange(N)
})
scatter_sns = sns.lmplot("x", "y",
scatter_kws={"s": data["size"]},
robust=False, # slow if true
data=data, size=8)
fig = plt.gcf()
tooltip = mpld3.plugins.PointLabelTooltip(fig, labels=list(data.label))
mpld3.plugins.connect(fig, tooltip)
mpld3.display(fig)
def kmeans_cluster(terms, description_tokens, tfidf_matrix, titles, bookobj_tokens_dict):
"""Kmeans algorithm used to create clusters of documents using scikitlearn.
Datapoints plotted using matplotlibd3."""
######################
### KMeans Cluster ###
######################
from sklearn.metrics.pairwise import cosine_similarity
# # dist is defined as 1 - the cosine similarity of each document. Cosine similarity is measured against
# # the tf-idf matrix can be used to generate a measure of similarity between each document and the
# # other documents in the corpus (each synopsis among the synopses). Subtracting it from 1 provides
# # cosine distance which I will use for plotting on a euclidean (2-dimensional) plane.
dist = 1 - cosine_similarity(tfidf_matrix)
num_clusters = 8
km = KMeans(n_clusters = num_clusters)
km.fit(tfidf_matrix)
clusters = km.labels_.tolist()
print "clusters, ", clusters
joblib.dump(km, 'doc_cluster.pkl')
km = joblib.load('doc_cluster.pkl')
clusters = km.labels_.tolist()
books = {'title':titles, 'synopsis':description_tokens,'cluster':clusters}
print "books, ", books
frame = pd.DataFrame(books,index=[clusters],columns=['title','cluster'])
frame['cluster'].value_counts()
grouped = frame['title'].groupby(frame['cluster'])
#############################
### Top Terms Per Cluster ###
#############################
print "Top terms per cluster:"
print
order_centroids = km.cluster_centers_.argsort()[:, ::-1]
print "order centroids, ", order_centroids
totalvocab_tokenized_list = [word for token_sublist in bookobj_tokens_dict.values() for word in token_sublist]
print "total vocab tokenized list, ", totalvocab_tokenized_list
vocab_frame = pd.DataFrame({'words': totalvocab_tokenized_list}, index=totalvocab_tokenized_list)
print 'there are ' + str(vocab_frame.shape[0]) + ' items in vocab_frame'
print "num cluster, ", num_clusters
print "values, ", frame.ix
print order_centroids
graph_keys = [i for i in range(num_clusters)]
graph_values = []
for i in range(num_clusters):
print "Cluster %d words:" % i
the_terms = []
for ind in order_centroids[i, :3]: # top 3 words that are nearest to the cluster centroid
graph_terms = vocab_frame.ix[terms[ind].split(' ')].values.tolist()[0][0].encode('utf-8','ignore')
the_terms.append(graph_terms)
print "graph terms ", graph_terms
print "the terms, ", the_terms
graph_values.append(the_terms)
print
print
print "Cluster %d titles:" % i
df = frame.ix[i]['title']
if type(df) is str:
print ' %s,' % df
else:
for title in df.values.tolist():
print ' %s,' % title
print
print
print "graph values ", graph_values
# def multi_diminsional_scaling_for_2D_array(dist, graph_values, graph_keys):
#################################
### Multi-Dimensional Scaling ###
#################################
# # convert the dist matrix into a 2-dimensional array using MDS
MDS()
# # convert two components while plotting points in 2-D plane
# # 'precomputed' because provide a distance matrix
# # will also specify random_state so the plot is reproducible
mds = MDS(n_components=2, dissimilarity="precomputed", random_state=1)
print "mds, ", mds
pos = mds.fit_transform(dist) # shape (n_compoents, n_samples)
print "pos, ", pos
xs, ys = pos[:, 0], pos[:, 1]
#################################
### Visualizing Book Clusters ###
#################################
# # set up colors per clusters using a dict
cluster_colors = {0: '#1b9e77', 1: '#d95f02', 2: '#7570b3', 3: '#e7298a', 4: '#66a61e',
5:'#F7EC45', 6:'#2ee3b6', 7:'#cd82c0'}
# # set up cluster names using a dict
graph_values = [", ".join(term_list) for term_list in graph_values]
cluster_names = dict(zip(graph_keys, graph_values))
print "cluster names dictionary, ", cluster_names
# # create data frame that has the result of the MDS plus the cluster numbers and titles
df = pd.DataFrame(dict(x=xs, y=ys, label=clusters, title=titles))
# # group by cluster
groups = df.groupby('label')
# # define custom css to format the font and to remove the axis labeling
css = """
text.mpld3-text, div.mpld3-tooltip {
font-family:Arial, Helvetica, sans-serif;
}
g.mpld3-xaxis, g.mpld3-yaxis {
display: none; }
svg.mpld3-figure {
margin-left: 0px;}
"""
# Ploting using matplotlib
fig, ax = plt.subplots(figsize=(14,6)) #set plot size
ax.margins(0.03) # Optional, just adds 5% padding to the autoscaling
# iterate through groups to layer the plot
# note that I use the cluster_name and cluster_color dicts with the 'name' lookup
# to return the appropriate color/label
for name, group in groups:
points = ax.plot(group.x, group.y, marker='o', linestyle='', ms=18,
label=cluster_names[name], mec='none',
color=cluster_colors[name])
ax.set_aspect('auto')
labels = [i for i in group.title]
# set tooltip using points, labels and the already defined 'css' - see above
tooltip = mpld3.plugins.PointHTMLTooltip(points[0], labels,
voffset=10, hoffset=10, css=css)
# connect tooltip to fig
mpld3.plugins.connect(fig, tooltip, TopToolbar())
# set tick marks as blank
ax.axes.get_xaxis().set_ticks([])
ax.axes.get_yaxis().set_ticks([])
#set axis as blank
ax.axes.get_xaxis().set_visible(False)
ax.axes.get_yaxis().set_visible(False)
ax.legend(numpoints=1, title='') # show legend with only one dot
mpld3.display() # show the plot
# uncomment the below to export to html
graph_html = mpld3.fig_to_html(fig)
print "KMEANS CLUSTER GRAPH HTML", graph_html
return graph_html
def parallel_coordinates(data_sets, colors=None, columNames=None, alpha=None):
dims = len(data_sets[0])
x = range(dims)
fig, axes = plt.subplots(1, dims - 1, sharey=False)
if colors is None:
colors = ['r-'] * len(data_sets)
# Calculate the limits on the data
min_max_range = list()
for m in zip(*data_sets):
mn = min(m)
mx = max(m)
if mn == mx:
mn -= 0.5
mx = mn + 1.
r = float(mx - mn)
min_max_range.append((mn, mx, r))
# Normalize the data sets
norm_data_sets = list()
for ds in data_sets:
nds = []
for dimension, value in enumerate(ds):
v = (value -
min_max_range[dimension][0]) / min_max_range[dimension][2]
nds.append(v)
norm_data_sets.append(nds)
data_sets = norm_data_sets
# Plot the datasets on all the subplots
for i, ax in enumerate(axes):
for dsi, d in enumerate(data_sets):
ax.plot(x, d, c=colors[dsi], alpha=alpha[dsi])
ax.set_xlim([x[i], x[i + 1]])
# Set the x axis ticks
for dimension, (axx, xx) in enumerate(zip(axes, x[:-1])):
axx.xaxis.set_major_locator(ticker.FixedLocator([xx]))
ticks = len(axx.get_yticklabels())
labels = list()
step = min_max_range[dimension][2] / (ticks - 3)
mn = min_max_range[dimension][0]
for i in range(-1, ticks):
v = mn + i * step
labels.append('%6.2f' % v)
axx.set_yticklabels(labels)
# Move the final axis' ticks to the right-hand side
axx = plt.twinx(axes[-1])
dimension += 1
axx.xaxis.set_major_locator(ticker.FixedLocator([x[-2], x[-1]]))
ticks = len(axx.get_yticklabels())
step = min_max_range[dimension][2] / (ticks - 1)
mn = min_max_range[dimension][0]
labels = ['%6.2f' % (mn + i * step) for i in range(ticks)]
axx.set_yticklabels(labels)
i = 0
for col in columNames[:-2]:
plt.sca(axes[i])
plt.xticks([i], (col, ), rotation='vertical')
i += 1
plt.sca(axes[i])
plt.xticks([i, i + 1], columNames[i:], rotation='vertical')
#color labels
plt.plot([], [], color='r', label='Infeasible')
plt.plot([], [], color='b', label='Feasible')
plt.plot([], [], color='g', label='Non-dominated')
#delete whitespace
plt.subplots_adjust(wspace=0)
#title
plt.suptitle('Parallel Coordinate Plot')
plt.legend(bbox_to_anchor=(1.6, 1), loc=2, borderaxespad=0.)
# fig.savefig("paralelcoordinate1.pdf",dpi=600,bbox_inches='tight')
#fig.savefig("paralelcoordinate")
mpld3.display(fig)
def writeResults(fn, userID, batchID):
Con2 = DBconnections.openDB()
cursor2 = Con2.cursor()
#get total number of reads
queryTotal = "SELECT SUM(seqcount) As TotalReads FROM tempcontent WHERE userID = {}".format(userID)
#print queryTotal
qLocus = "SELECT locus FROM tempcontent WHERE userID = {} Group by locus".format(userID)
cursor2.execute (queryTotal)
tReads = cursor2.fetchone()
totalReads = tReads[0]
#print "<br/>total reads: " + str(totalReads)
cursor2.execute (qLocus)
locuslinks = cursor2.fetchall()
links = 0
# View Locus select list
print "<hr/><br/><form action='' method='post' name='locfrm' id='locfrm' enctype='multipart/form-data' >" +\
"<b>View Locus: </b><select id='locusname' name='locusname' onchange='javascript: getlocus(this);'>" +\
"<option value=''"
if locusname == "":
print "selected>"
else:
print ">"
print "All</option>"
for lcs in locuslinks:
print "<option value='" + str(lcs[0]) + "' "
if locusname == str(lcs[0]):
print "selected"
print ">" + str(lcs[0]) + "</option>"
print "</select>"
# Allele Ratio Filter select list
print " <b>Allele Ratio Filter: </b>" +\
"<select id='filter' name='filter' style='width:100px;' onchange='javascript: getFilter(this);'>"
num = 0
perctg = 0
for n in range(0,12):
print "<option value='" + str(num) + "'"
if str(filter) == str(num):
print "selected"
print ">"
if num == 0:
print "Nothing"
else:
print "> " + str(num)
print "</option>"
num = num + 0.001
print "</select>"
# Locus Filter list
print " <b>Locus Ratio Filter: </b>" +\
"<select id='locfilter' name='locfilter' style='width:100px;' onchange='javascript: getLocFilter(this);'>"
num = 0
perctg = 0
for n in range(0,4):
print "<option value='" + str(num) + "'"
if str(locfilter) == str(num):
print "selected"
print ">"
if num == 0:
print "Nothing"
else:
print "> " + str(num)
print "</option>"
num = num + 0.01
print "</select>"
print "<br/><input type='hidden' name='idnumber' id='idnumber' value='" + batchID + "'>" +\
"<input type='hidden' name='fileholder' id='fileholder' value='" + fileholder + "'>" +\
"</form>"
if locusname == "":
queryCount = "SELECT locus, SUM(seqcount) As TotalReads FROM tempcontent WHERE userID = {} Group by locus".format(userID) +\
" ORDER BY locus"
else:
queryCount = "SELECT locus, SUM(seqcount) As TotalReads FROM tempcontent WHERE " +\
"locus = '" + locusname + "' AND " +\
"userID = {} Group by locus".format(userID) +\
" ORDER BY locus"
cursor2.execute (queryCount)
Readresults = cursor2.fetchall()
for rec in Readresults:
locus = rec[0]
sCount = rec[1]
# sort and count number of reads
#filename locus allele read_dir sequence seq_Len reads allele_Count allele_ratio total_ratio num_repeats
query = "SELECT tempcontent.locus, allele, readdir, " +\
"tempcontent.seq as seq, length(tempcontent.seq) as seqLen, SUM(seqcount) as seqCounts, " +\
"((SUM(tempcontent.seqcount))/{}.0)".format(sCount) + " As allele_ratio, ((SUM(tempcontent.seqcount))/{}.0)".format(totalReads) + " As total_ratio " +\
"FROM tempcontent " +\
"WHERE tempcontent.locus = '" + locus + "' AND userID = {}".format(userID) +\
" Group by allele, locus, readDir, tempcontent.seq "
#if filter > 0:
#query = query + " HAVING ((SUM(tempcontent.seqcount))/{}.0)".format(sCount) + " > " + filter
query = query + " Order by length(tempcontent.seq), tempcontent.seq, readdir, SUM(seqcount) desc "
cursor2.execute (query)
getRecords = cursor2.fetchall()
print "<br/><table style='border-collapse:collapse; border: solid 1px black;font-size:12px;'>"
count = 0
aH = ""
lH = ""
sH = ""
rdH = ""
FRRH = ""
slH = 0
scH = 0
arH = 0
trH = 0
flag = False
for seqRecord in getRecords:
locus = seqRecord[0]
allele = seqRecord[1]
readdir = seqRecord[2]
seq = seqRecord[3]
seqLen = seqRecord[4]
seqCounts = seqRecord[5]
alleleRatio = seqRecord[6]
totalRatio = seqRecord[7]
locusRatio = sCount/totalReads
if count == 0:
print "<tr style='background-color: #cccccc;'><td colspan='8' style='border-style:solid;border-width: 0px 0px 1px 0px;'><b>" +\
locus + "</b><br/>" +\
"<b>Allele total: </b>" + str(sCount) + " <b>Total Count:</b> " + str(totalReads) +\
" <b>Locus Ratio: </b>" + "{0:.4f}".format(locusRatio) + "</td></tr>"
if float(locusRatio) > float(locfilter):
print "<tr style='background-color:#FAEBD7;border:1px solid black;'><th style='padding-right:5px;'>Allele</th><th style='padding-right:5px;'>locus</th>" +\
"<th style='padding-right:8px;'>Seq</th><th style='padding-right:8px;'>Seq<br/>Length</th>" +\
"<th style='padding-right:8px;'>Seq<br/>Counts</th><th style='padding-right:8px;'>FWD/REV</th>" +\
"<th style='padding-right:8px;'>Allele<br/>Ratio</th><th style='padding-right:8px;'>Total<br/>Ratio</th></tr>"
aH = allele
lH = locus
sH = seq
slH = seqLen
scH = seqCounts
arH = alleleRatio
trH = totalRatio
flag = True
if float(locusRatio) > float(locfilter):
if count > 0:
if readdir == 'REV' and seq == sH:
aH = allele
lH = locus
sH = seq
slH = seqLen
FR = scH/(scH + seqCounts)
RR = seqCounts/(scH + seqCounts)
FRRH = "{0:.4f}".format(FR) + "/" + "{0:.4f}".format(RR)
scH = scH + seqCounts
arH = arH + alleleRatio
trH = trH + totalRatio
if float(arH) > float(filter):
print "<tr><td style='padding-left:5px;padding-right:5px;'>{}</th>".format(aH)
print "<th style='padding-right:5px;'>{}</th>".format(lH)
print "<th style='padding-right:5px;'>{}</th>".format(sH)
print "<th style='padding-right:8px;'>{}</th>".format(slH)
print "<th style='padding-right:8px;'>{}</th>".format(scH)
print "<th style='padding-right:8px;'>{}</th>".format(FRRH)
print "<th style='padding-right:8px;'>{}</th>".format(arH)
print "<th style='padding-right:8px;'>{}</th></tr>".format(trH)
flag = False
else:
if flag == True :
if float(arH) > float(filter):
print "<tr><td style='padding-left:5px;padding-right:5px;'>{}</th>".format(aH)
print "<th style='padding-right:5px;'>{}</th>".format(lH)
print "<th style='padding-right:5px;'>{}</th>".format(sH)
print "<th style='padding-right:8px;'>{}</th>".format(slH)
print "<th style='padding-right:8px;'>{}</th>".format(scH)
print "<th style='padding-right:8px;'>{}</th>".format(FRRH)
print "<th style='padding-right:8px;'>{}</th>".format(arH)
print "<th style='padding-right:8px;'>{}</th></tr>".format(trH)
flag = False
aH = allele
lH = locus
sH = seq
slH = seqLen
scH = seqCounts
arH = alleleRatio
trH = totalRatio
if readdir == "FWD":
FRRH = "1/0"
flag = True
else:
FRRH = "0/1"
flag = False
if flag == False:
if float(arH) > float(filter):
print "<tr><td style='padding-left:5px;padding-right:5px;'>{}</th>".format(aH)
print "<th style='padding-right:5px;'>{}</th>".format(lH)
print "<th style='padding-right:5px;'>{}</th>".format(sH)
print "<th style='padding-right:5px;'>{}</th>".format(slH)
print "<th style='padding-right:5px;'>{}</th>".format(scH)
print "<th style='padding-right:5px;'>{}</th>".format(FRRH)
print "<th style='padding-right:5px;'>{}</th>".format(arH)
print "<th style='padding-right:5px;'>{}</th></tr>".format(trH)
flag = False
count += 1
else:
print "<tr style='background-color:#ccffff'><td colspan='8' style='border-top:1px solid black;'>No Data</td></tr>"
break
print "</table><br/>"
N = 5
menMeans = (20, 35, 30, 35, 27)
menStd = (2, 3, 4, 1, 2)
ind = np.arange(N) # the x locations for the groups
width = 0.35 # the width of the bars
fig, ax = plt.subplots()
rects1 = ax.bar(ind, menMeans, width, color='r', yerr=menStd)
womenMeans = (25, 32, 34, 20, 25)
womenStd = (3, 5, 2, 3, 3)
rects2 = ax.bar(ind + width, womenMeans, width, color='y', yerr=womenStd)
# add some text for labels, title and axes ticks
ax.set_ylabel('Scores')
ax.set_title('Scores by group and gender')
ax.set_xticks(ind + width)
ax.set_xticklabels(('G1', 'G2', 'G3', 'G4', 'G5'))
ax.legend((rects1[0], rects2[0]), ('Men', 'Women'))
autolabel(rects1)
autolabel(rects2)
#plt.show()
mpld3.display(plt,True,False)
cursor2.close()
DBconnections.closeDB(Con2)