def production_envelope(self,
dataframe,
grid=None,
width=None,
height=None,
title=None,
points=None,
points_colors=None,
palette=None,
x_axis_label=None,
y_axis_label=None):
palette = self.get_option('palette') if palette is None else palette
width = self.get_option('width') if width is None else width
colors = self._palette(palette, len(dataframe.strain.unique()))
plot = aes(data=dataframe,
ymin="lb",
ymax="ub",
x="value",
color=scale_colour_manual(colors)) + geom_area()
if title:
plot += geom_tile(title)
if x_axis_label:
plot += scale_x_continuous(name=x_axis_label)
if y_axis_label:
plot += scale_y_continuous(name=y_axis_label)
return plot
def signature_data_plot(sd):
import ggplot as gg
aes = gg.aes(x='set_exp', y='not_exp', color='pearson_r')
return gg.ggplot(aes, data=sd) \
+ gg.geom_point(size=15) \
+ gg.scale_color_gradient(low='yellow', high='red') \
+ gg.scale_x_log() + gg.scale_x_continuous(limits=(0.5, 10000)) \
+ gg.scale_y_log() + gg.scale_y_continuous(limits=(0.05, 10000))
def signature_data_plot(sd):
import ggplot as gg
aes = gg.aes(x='set_exp', y='not_exp', color='pearson_r')
return gg.ggplot(aes, data=sd) \
+ gg.geom_point(size=15) \
+ gg.scale_color_gradient(low='yellow', high='red') \
+ gg.scale_x_log() + gg.scale_x_continuous(limits=(0.5, 10000)) \
+ gg.scale_y_log() + gg.scale_y_continuous(limits=(0.05, 10000))
def plot_timeline(scenes):
# Plot character vs scene timelime
# NB: due to limitations in Python ggplot we need to plot with scene on y-axis
# in order to label x-ticks by character.
# scale_x_continuous and scale_y_continuous behave slightly differently.
print (gg.ggplot(gg.aes(y='scene', x='character_code'), data=scenes) +
gg.geom_point() + gg.labs(x='Character', y='Scene') +
gg.scale_x_continuous(
labels=scenes['character'].cat.categories.values.tolist(),
breaks=range(len(scenes['character'].cat.categories))) +
gg.theme(axis_text_x=gg.element_text(angle=30, hjust=1, size=10)))
def scatter(self, dataframe, x=None, y=None, width=None, height=None, color=None, title='Scatter', xaxis_label=None,
yaxis_label=None):
color = self.__default_options__.get('palette', None) if color is None else color
width = self.__default_options__.get('width', None) if width is None else width
gg = ggplot(dataframe, aes(x, y)) + geom_point(color=color, alpha=0.6) + ggtitle(title)
if xaxis_label:
gg += scale_x_continuous(name=xaxis_label)
if yaxis_label:
gg += scale_y_continuous(name=xaxis_label)
return gg
def plot_age_speed(df):
num_rows = df.shape[0]
title = 'age v speed'
print ggplot(df, aes(s.AGE_COL_NAME, s.SPEED_COL_NAME)) + \
ggtitle(_make_title(title, num_rows))+ \
geom_point(colour='steelblue') + \
scale_x_continuous(
# breaks=[10,20,30],
# labels=["horrible", "ok", "awesome"]
)
return df
def plot_distance_trip_time(df):
num_rows = df.shape[0]
title = 'trip duration v distance travelled'
print ggplot(df, aes(s.TRIP_DURATION_COL, s.DISTANCE_TRAVELED_COL_NAME)) + \
ggtitle(_make_title(title, num_rows))+ \
stat_smooth(colour="red") + \
geom_point(colour='steelblue') + \
scale_x_continuous(
# breaks=[10,20,30],
#labels=["horrible", "ok", "awesome"]
)
return df
def graph1(score_data):
""" Average score as time goes on;
Creates and returns graph 1, a line graph. """
date_column = score_data[0][find_time_stamp(score_data)]
data = DataFrame(score_data[1:], columns=score_data[0])
# Get all columns that arlabels = date_format("%Y-%m-%d")e numerical
# questions so we know what to graph
num_questions = data.select_dtypes(include=['int64']).columns.values
# Melt data so that each question is in a seperate row
new_data = pd.melt(data,
id_vars=date_column,
value_vars=num_questions,
var_name="Question",
value_name="Score")
# Convert date string into an actual date type
new_data[date_column] = pd.to_datetime(new_data[date_column],
format="%m/%d/%Y")
# Group all rows with same date and question, and then take the average.
new_data = new_data.groupby([date_column, 'Question']).mean().reset_index()
new_data['All'] = "Indiviual Questions"
new_data2 = new_data.groupby(date_column).mean().reset_index()
new_data2['Question'] = "All Questions"
new_data2['All'] = "Average of All Questions"
new_data = pd.concat([new_data, new_data2])
new_data[date_column] = new_data[date_column].astype('int64')
# Create time graph with seperate lines for each question
ret = ggplot.ggplot(ggplot.aes(x=date_column, y="Score", colour="Question"), new_data) +\
ggplot.geom_point() +\
ggplot.geom_line() +\
ggplot.facet_grid("All") +\
ggplot.scale_x_continuous(labels=[""], breaks=0) +\
ggplot.labs(x="Time", y="Average Question Score") +\
ggplot.ggtitle("Question Scores Over Time")
return ret
def scatter(self,
dataframe,
x=None,
y=None,
width=None,
height=None,
color=None,
title='Scatter',
xaxis_label=None,
yaxis_label=None,
label=None):
color = self.__default_options__.get('palette',
None) if color is None else color
width = self.__default_options__.get('width',
None) if width is None else width
gg = ggplot(dataframe, aes(x, y)) + geom_point(
color=color, alpha=0.6) + ggtitle(title)
if xaxis_label:
gg += scale_x_continuous(name=xaxis_label)
if yaxis_label:
gg += scale_y_continuous(name=xaxis_label)
return gg
values_dict = {
"significant": coefficients[feature]["significant"],
"insignificant": coefficients[feature]["unsignificant"]
}
df = pd.DataFrame.from_dict(values_dict, orient='index')
df = df.transpose()
df = pd.melt(df)
df['feature'] = feature
dfs_to_concat.append(df)
master_df = pd.concat(dfs_to_concat)
# histogram
p = ggplot(aes(x='value', fill='variable', color='variable'), data=master_df)
p += geom_histogram(bins=25, alpha=0.5)
p += scale_x_continuous(limits=(-25, 25))
p += ggtitle("sarimax coefficient magnitude distribution")
p += facet_wrap("feature", ncol=3, scales="free")
p += labs(x=" ", y=" ")
# visuals
t = theme_gray()
t._rcParams['font.size'] = 10
t._rcParams['font.family'] = 'monospace'
p += t
p.save("arima_1/" + "histogram.png")
# boxplot
p = ggplot(aes(x='variable', y='value'), data=master_df)
p += geom_boxplot()
import pandas as pd
import numpy as np
# from source import view_and_print_output
import ggplot as gg
df = pd.DataFrame()
for num_layers, num_nodes in [(2, 50), (2, 100), (2, 150), (2, 200), (4, 50), (4, 100), (4, 150), (4, 200)]:
file_coarse = '../../data/coarse_lambda_dropout_' + str(num_layers) + '_' + str(num_nodes) + '.txt'
newdata = pd.read_csv(file_coarse)
newdata = newdata.sort_values(by='validation error', ascending=True)
newdata['lambda'] = np.log10(newdata['lambda'])
newdata['index'] = (np.arange(len(newdata), dtype='float')/len(newdata))**3
newdata['config'] = str(num_layers * 100 + num_nodes) + ' ' + str(num_layers) + ' ' + str(num_nodes)
df = df.append(newdata)
print(df.sort_values(by='validation error', ascending=False).head(20))
p = gg.ggplot(gg.aes(x='lambda', y='dropout prob', color='index'), data=df) + \
gg.geom_point() + \
gg.xlab('lambda') + \
gg.ylab('dropout prob') + \
gg.scale_x_continuous(limits=(-5, 2)) + \
gg.facet_wrap('config')
print(p)
# Conclusion: ignore dropout
t * len(count_tops) + len(count_tops)))
probs_list.append(probs_t)
# Calculate KL divergences
kl_mle_list.append(stats.entropy(true_bins_t, mle_probs_vals))
kl_nn_list.append(stats.entropy(true_bins_t, nn_probs_t))
probs = pd.concat(probs_list)
# In[44]:
probs_tail = probs[probs.Tenor > 360]
gg.ggplot(probs_tail, gg.aes(x='Count Top', weight='Probs True')
) + gg.facet_grid('Tenor') + gg.geom_bar() + gg.geom_step(
gg.aes(y='Probs MLE', color='red')) + gg.geom_step(
gg.aes(y='Probs NN', color='blue')) + gg.scale_x_continuous(
limits=(0, len(count_tops)))
# In[57]:
# KL divergences
kl_df = pd.DataFrame({
'Tenor': range(0, t_end + 1),
'KL MLE': kl_mle_list,
'KL NN': kl_nn_list
})
print kl_df.head()
print kl_df.tail()
#%
# Plot KL divergences
def main():
parser = argparse.ArgumentParser(description="Draws displacement plots.",
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--limits', type=int, help="Maximum extent of the axes")
parser.add_argument('--no-plots', action='store_true', help="Don't save plots")
parser.add_argument('--summary', help='Save summary stats by file')
parser.add_argument('--imagetype', '-i', default='png', help="Extension to use for plots")
parser.add_argument('--pixels-per-micron', '--pixels', '-p', default=1.51, type=float,
help="Pixels per µm (length scale of tracked images)")
parser.add_argument('--minutes-per-frame', '--minutes', '-m', default=10, type=float,
help="Minutes between each frame of the tracked images")
parser.add_argument('--plot-titles', type=argparse.FileType('r'),
help="CSV file with filename and title columns")
parser.add_argument('--style', action='append', default=[],
choices=['theme-bw', 'no-terminal-dot'],
help='Change style options for the plot.')
parser.add_argument('--tick-breaks', '--ticks', '-t', nargs=3, type=int,
metavar=('start', 'end', 'step'),
help="Beginning and end tick breaks on displacement plots")
parser.add_argument('--plot-text', type=int, default=8,
help='Plot text size (pt)')
parser.add_argument('--plot-height', type=float, default=1.81,
help='Plot height (in)')
parser.add_argument('--plot-width', type=float, default=2.5,
help='Plot width (in)')
parser.add_argument('infile', nargs='+', help="File(s) to process.")
args = parser.parse_args()
style = {argument: True for argument in args.style}
plot_titles = pd.read_csv(args.plot_titles, index_col="filename") if args.plot_titles else None
all_dfs = []
for filename in args.infile:
# there has to be a better pattern for this
try:
df = read_mtrackj_mdf(filename)
except ValueError:
try:
df = read_mtrack2(filename)
except Exception:
df = read_manual_track(filename)
centered = center(df)
centered.to_csv(filename + '.centered')
if not args.no_plots:
g = displacement_plot(centered, limits=args.limits, style=style)
g += gg.theme(axis_text=gg.element_text(size=args.plot_text))
g += gg.labs(x='px', y='px')
if args.tick_breaks:
g += gg.scale_x_continuous(breaks=range(*args.tick_breaks))
g += gg.scale_y_continuous(breaks=range(*args.tick_breaks))
if plot_titles is not None and filename in plot_titles.index:
g += gg.labs(title=plot_titles.ix[filename, 'title'])
g.save('{}.{}'.format(filename, args.imagetype),
width=args.plot_width, height=args.plot_height)
centered['filename'] = filename
all_dfs.append(centered)
mega_df = pd.concat(all_dfs, ignore_index=True)
stats_for = lambda x: stats(x, length_scale=args.pixels_per_micron,
time_scale=args.minutes_per_frame)
obj_stats = (mega_df.groupby('filename', sort=False)
.apply(stats_for)
.reset_index())
summary_by_file = obj_stats.groupby('filename').apply(summary)
if args.summary:
summary_by_file.to_csv(args.summary, index=False)
print("# Produced by {} at {}".format(' '.join(sys.argv), time.ctime()))
print("# {} pixels per micron, {} minutes per frame".
format(args.pixels_per_micron, args.minutes_per_frame))
print("# distance units are microns; velocity units are microns/hour")
obj_stats.to_csv(sys.stdout, index=False)