def export_figure(self, output_file):
"""
Requires a working *selenium* driver (https://www.selenium.dev/selenium/docs/api/py/).
Related attributes are `selenium_webdriver`, `figure_export_width` and `figure_export_height`.
"""
export_kwargs = {}
if self.selenium_webdriver is not None:
export_kwargs['webdriver'] = self.selenium_webdriver()
if self.figure_export_width is not None:
export_kwargs['width'] = self.figure_export_width
if self.figure_export_height is not None:
export_kwargs['height'] = self.figure_export_height
#self.set_export_status('figure', 'exporting...')
try:
doc = row(self.main_figure, self.colorbar_figure)
from bokeh.io import export
if output_file.endswith('.png'):
export.export_png(doc, filename=output_file, **export_kwargs)
elif output_file.endswith('.svg'):
export.export_svg(doc, filename=output_file, **export_kwargs)
else:
raise NotImplementedError("format '{}' not supported".format(
os.path.splitext(output_file)[1]))
self.set_export_status('figure', 'done')
except (KeyboardInterrupt, SystemExit):
raise
except:
traceback.print_exc()
self.set_export_status('figure', 'failed')
def export_figure(self, output_file):
"""
Requires a working *selenium* driver (https://www.selenium.dev/selenium/docs/api/py/).
Related attributes are `selenium_webdriver`, `figure_export_width` and `figure_export_height`.
"""
export_kwargs = {}
if self.selenium_webdriver is not None:
try:
from importlib import import_module
options = import_module(
self.selenium_webdriver.__module__[:-9] + "options")
options = options.Options()
options.headless = True
webdriver = self.selenium_webdriver(options=options)
except (ImportError, AttributeError):
import selenium
if self.selenium_webdriver in (
selenium.webdriver.Safari,
selenium.webdriver.Edge,
):
pass
else:
import warnings, traceback
warnings.warn(
"could not access the webdriver"
"s options:\n" + traceback.format_exc(),
ImportWarning,
)
webdriver = self.selenium_driver()
export_kwargs["webdriver"] = webdriver
if self.figure_export_width is not None:
export_kwargs["width"] = self.figure_export_width
if self.figure_export_height is not None:
export_kwargs["height"] = self.figure_export_height
# self.set_export_status('figure', 'exporting...')
try:
doc = row(self.main_figure, self.colorbar_figure)
from bokeh.io import export
if output_file.endswith(".png"):
export.export_png(doc, filename=output_file, **export_kwargs)
elif output_file.endswith(".svg"):
export.export_svg(doc, filename=output_file, **export_kwargs)
else:
raise NotImplementedError("format '{}' not supported".format(
os.path.splitext(output_file)[1]))
self.set_export_status("figure", "done")
except (KeyboardInterrupt, SystemExit):
raise
except:
traceback.print_exc()
self.set_export_status("figure", "failed")
def draw_2d_chart(idx, x, cluster_output_path, k):
driver = webdriver.Chrome(os.path.join(BASE_DIR, "chromedriver"),
options=opts)
tsne = TSNE(random_state=42)
points = tsne.fit_transform(x)
t_df = pd.DataFrame(points, index=range(len(x)), columns=["x", "y"])
t_df["cluster_no"] = idx
colors = [colormap[x] for x in t_df["cluster_no"]]
t_df["color"] = colors
plot_data = ColumnDataSource(data=t_df.to_dict(orient="list"))
p = figure(
# title='TSNE Twitter BIO Embeddings',
plot_width=1200,
plot_height=1200,
active_scroll="wheel_zoom",
output_backend="svg",
)
p.add_tools(HoverTool(tooltips="@title"))
p.circle(
source=plot_data,
x="x",
y="y",
line_alpha=0.9,
fill_alpha=0.9,
size=8,
# size="radius",
fill_color="color",
line_color="color",
)
p.title.text_font_size = value("16pt")
p.xaxis.visible = True
p.yaxis.visible = True
p.background_fill_color = None
p.border_fill_color = None
p.grid.grid_line_color = None
p.outline_line_color = None
# tsne_plot.grid.grid_line_color = None
# tsne_plot.outline_line_color = None
p.toolbar.logo = None
p.toolbar_location = None
export_svg(
p,
filename=os.path.join(cluster_output_path, f"cluster2d-{k}.svg"),
webdriver=driver,
)
export_png(
p,
filename=os.path.join(cluster_output_path, f"cluster2d-{k}.png"),
webdriver=driver,
)
def write_chart(output_file_dir, title, p, driver):
output_dir = os.path.join(output_file_dir, title)
if not os.path.isdir(output_dir):
os.mkdir(output_dir)
export_png(
p,
webdriver=driver,
timeout=500,
filename=os.path.join(
output_dir,
f"{title}.png",
),
)
export_svg(
p,
webdriver=driver,
timeout=500,
filename=os.path.join(
output_dir,
f"{title}.svg",
),
)
def write_cross_chart(df, cluster_output_path, k):
height = 1600
width = 1600
driver = webdriver.Chrome(os.path.join(BASE_DIR, "chromedriver"),
options=opts)
x = df.c3.to_list()
y = df.c1.to_list()
clusters = df.cluster.to_list()
plot = figure(
# title='TSNE Twitter BIO Embeddings',
plot_width=width,
plot_height=height,
active_scroll="wheel_zoom",
# x_range=r,
# y_range=r,
output_backend="svg",
)
plot.add_tools(HoverTool(tooltips="@title"))
new_x = []
new_y = []
for coord in zip(x, y):
x_coord, y_coord = coord
x_rand = random.uniform(-(0.5**0.5), 0.5**0.5)
y_rand_range = (0.5 - x_rand**2)**0.5
y_rand = random.uniform(-y_rand_range, y_rand_range)
new_x.append(x_coord + x_rand)
new_y.append(y_coord + y_rand)
colors = [colormap[clusters[i]] for i in range(len(new_y))]
source = ColumnDataSource(data={"x": new_x, "y": new_y, "color": colors})
plot.scatter(
source=source,
x="x",
y="y",
line_alpha=0.6,
fill_alpha=0.6,
size=10,
color="color",
)
# size
# count_map = defaultdict(int)
# for coord in zip(x, y):
# count_map[coord] += 1 * 0.5
# source = ColumnDataSource(
# data={
# "x": [k[0] for k in count_map.keys()],
# "y": [k[1] for k in count_map.keys()],
# "size": list(count_map.values()),
# }
# )
# plot.scatter(
# source=source,
# x="x",
# y="y",
# line_alpha=0.6,
# fill_alpha=0.6,
# size="size",
# )
plot.yaxis.axis_label_text_font_size = "25pt"
plot.yaxis.major_label_text_font_size = "25pt"
plot.xaxis.axis_label_text_font_size = "25pt"
plot.xaxis.major_label_text_font_size = "25pt"
plot.title.text_font_size = value("32pt")
plot.xaxis.visible = True
# plot.xaxis.bounds = (0, 0)
plot.yaxis.visible = True
label_opts1 = dict(
x_offset=0,
y_offset=750,
text_font_size="30px",
)
msg1 = "C1"
caption1 = Label(text=msg1, **label_opts1)
label_opts2 = dict(
x_offset=0,
y_offset=-750,
text_font_size="30px",
)
msg2 = "-C1"
caption2 = Label(text=msg2, **label_opts2)
label_opts3 = dict(
x_offset=750,
y_offset=0,
text_font_size="30px",
)
msg3 = "C3"
caption3 = Label(text=msg3, **label_opts3)
label_opts4 = dict(
x_offset=-750,
y_offset=0,
text_font_size="30px",
)
msg4 = "-C3"
caption4 = Label(text=msg4, **label_opts4)
plot.add_layout(caption1, "center")
plot.add_layout(caption2, "center")
plot.add_layout(caption3, "center")
plot.add_layout(caption4, "center")
plot.background_fill_color = None
plot.border_fill_color = None
plot.grid.grid_line_color = None
plot.outline_line_color = None
plot.yaxis.fixed_location = 0
plot.xaxis.fixed_location = 0
plot.toolbar.logo = None
plot.toolbar_location = None
export_svg(
plot,
filename=os.path.join(cluster_output_path, f"cross-{k}.svg"),
webdriver=driver,
height=height,
width=width,
)
export_png(
plot,
filename=os.path.join(cluster_output_path, f"cross-{k}.png"),
webdriver=driver,
height=height,
width=width,
)
def draw_vectors():
driver = webdriver.Chrome(os.path.join(BASE_DIR, "chromedriver"),
options=options)
df = pd.read_csv(os.path.join(OUTPUTS_DIR,
"normalized_future_vectors.csv"))
filter_list = {
(5, 6),
(5, 7),
(6, 7),
(8, 9),
(8, 10),
(9, 10),
(11, 12),
(11, 13),
(12, 13),
}
comb = list(combinations(range(5, len(df.columns)), 2))
comb = [c for c in comb if c not in filter_list]
for idx, coord in enumerate(comb, 1):
x, y = coord
X = df[df.columns[x]].to_list()
Y = df[df.columns[y]].to_list()
tsne_df = pd.DataFrame(zip(X, Y),
index=range(len(X)),
columns=["x_coord", "y_coord"])
tsne_df["title"] = df["title"].to_list()
tsne_df["cluster_no"] = df["cluster"].to_list()
colormap = {3: "#ffee33", 2: "#00a152", 1: "#2979ff", 0: "#d500f9"}
# colormap = {3: "#bdbdbd", 2: "#bdbdbd", 1: "#bdbdbd", 0: "#d500f9"}
# colormap = {3: "#bdbdbd", 2: "#bdbdbd", 1: "#2979ff", 0: "#bdbdbd"}
# colormap = {3: "#bdbdbd", 2: "#00a152", 1: "#bdbdbd", 0: "#bdbdbd"}
# colormap = {3: "#ffee33", 2: "#bdbdbd", 1: "#bdbdbd", 0: "#bdbdbd"}
only_one_cluster = pd.DataFrame(tsne_df.loc[tsne_df.cluster_no == 3])
colors = [colormap[x] for x in only_one_cluster["cluster_no"]]
only_one_cluster["color"] = colors
plot_data = ColumnDataSource(data=only_one_cluster.to_dict(
orient="list"))
plot = figure(
# title='TSNE Twitter BIO Embeddings',
plot_width=1600,
plot_height=1600,
active_scroll="wheel_zoom",
output_backend="svg",
x_range=(-1.1, 1.1),
y_range=(-1.1, 1.1),
)
plot.add_tools(HoverTool(tooltips="@title"))
plot.circle(
source=plot_data,
x="x_coord",
y="y_coord",
line_alpha=0.6,
fill_alpha=0.6,
size=20,
fill_color="color",
line_color="color",
)
plot.yaxis.axis_label_text_font_size = "25pt"
plot.yaxis.major_label_text_font_size = "25pt"
plot.xaxis.axis_label_text_font_size = "25pt"
plot.xaxis.major_label_text_font_size = "25pt"
start_x, end_x = df.columns[x].split("|")
start_y, end_y = df.columns[y].split("|")
start_x = start_x.strip()
end_x = end_x.strip()
start_y = start_y.strip()
end_y = end_y.strip()
plot.title.text_font_size = value("32pt")
plot.xaxis.visible = True
# plot.xaxis.bounds = (0, 0)
plot.yaxis.visible = True
label_opts1 = dict(
x_offset=0,
y_offset=750,
text_font_size="30px",
)
msg1 = end_y
caption1 = Label(text=msg1, **label_opts1)
label_opts2 = dict(
x_offset=0,
y_offset=-750,
text_font_size="30px",
)
msg2 = start_y
caption2 = Label(text=msg2, **label_opts2)
label_opts3 = dict(
x_offset=600,
y_offset=0,
text_font_size="30px",
)
msg3 = end_x
caption3 = Label(text=msg3, **label_opts3)
label_opts4 = dict(
x_offset=-750,
y_offset=0,
text_font_size="30px",
)
msg4 = start_x
caption4 = Label(text=msg4, **label_opts4)
plot.add_layout(caption1, "center")
plot.add_layout(caption2, "center")
plot.add_layout(caption3, "center")
plot.add_layout(caption4, "center")
plot.background_fill_color = None
plot.border_fill_color = None
plot.grid.grid_line_color = None
plot.outline_line_color = None
plot.yaxis.fixed_location = 0
plot.xaxis.fixed_location = 0
plot.toolbar.logo = None
plot.toolbar_location = None
print(idx)
export_svg(
plot,
filename=f"svgs/{idx}.svg",
webdriver=driver,
height=1600,
width=1600,
)
export_png(
plot,
filename=f"pngs/{idx}.png",
webdriver=driver,
height=1600,
width=1600,
)
def draw_chart(df):
driver = webdriver.Chrome(os.path.join(BASE_DIR, "chromedriver"))
X = df["wv"].to_list()
y = df["cluster"].to_list()
tsne_filepath = "tsne3000.pkl"
if not os.path.exists(tsne_filepath):
tsne = TSNE(random_state=42)
tsne_points = tsne.fit_transform(X)
with open(tsne_filepath, "wb+") as f:
pickle.dump(tsne_points, f)
else: # Cache Hits!
with open(tsne_filepath, "rb") as f:
tsne_points = pickle.load(f)
tsne_df = pd.DataFrame(
tsne_points, index=range(len(X)), columns=["x_coord", "y_coord"]
)
tsne_df["title"] = df["title"].to_list()
tsne_df["tokens_len"] = df["tokens_len"].to_list()
tsne_df["cluster_no"] = y
colormap = {0: "#ffee33", 1: "#00a152", 2: "#2979ff", 3: "#d500f9"}
colors = [colormap[x] for x in tsne_df["cluster_no"]]
tsne_df["color"] = colors
normalized = min_max_normalize(tsne_df.tokens_len.to_list())
tsne_df["radius"] = [5 + x * 10 for x in normalized]
print(tsne_df.to_dict(orient="list"))
plot_data = ColumnDataSource(data=tsne_df.to_dict(orient="list"))
print(plot_data)
tsne_plot = figure(
# title='TSNE Twitter BIO Embeddings',
plot_width=1200,
plot_height=1200,
active_scroll="wheel_zoom",
output_backend="svg",
)
tsne_plot.add_tools(HoverTool(tooltips="@title"))
tsne_plot.circle(
source=plot_data,
x="x_coord",
y="y_coord",
line_alpha=0.6,
fill_alpha=0.6,
size="radius",
fill_color="color",
line_color="color",
)
tsne_plot.title.text_font_size = value("16pt")
tsne_plot.xaxis.visible = True
tsne_plot.yaxis.visible = True
tsne_plot.background_fill_color = None
tsne_plot.border_fill_color = None
tsne_plot.grid.grid_line_color = None
tsne_plot.outline_line_color = None
# tsne_plot.grid.grid_line_color = None
# tsne_plot.outline_line_color = None
show(tsne_plot)
tsne_plot.toolbar.logo = None
tsne_plot.toolbar_location = None
export_svg(
tsne_plot, filename=f"cluster.svg", webdriver=driver,
)
export_png(
tsne_plot, filename=f"cluster.png", webdriver=driver,
)
def calculate_cluster_number():
driver = webdriver.Chrome(
os.path.join(BASE_DIR, "chromedriver"), options=opts
)
df = pd.read_csv(os.path.join(H_IN_DIRS, "happiness.csv"))
x = []
for row in df.iterrows():
idx, r = row
temp = []
for c in df.columns[1:-1]:
temp.append(r[c])
x.append(temp)
ok = 0
kmax = 10
maximum = 0
for k in range(2, kmax + 1):
kmeans = KMeans(n_clusters=k)
fit = kmeans.fit(x)
labels = fit.labels_
score = silhouette_score(x, labels, metric="euclidean")
idx = kmeans.fit_predict(x)
tsne = TSNE(random_state=42)
points = tsne.fit_transform(x)
t_df = pd.DataFrame(points, index=range(len(x)), columns=["x", "y"])
t_df["cluster_no"] = idx
colormap = {
0: "#f44336",
1: "#673ab7",
2: "#9c27b0",
3: "#e91e63",
4: "#3f51b5",
5: "#2196f3",
6: "#03a9f4",
7: "#00bcd4",
8: "#009688",
9: "#cddc39",
}
colors = [colormap[x] for x in t_df["cluster_no"]]
t_df["color"] = colors
plot_data = ColumnDataSource(data=t_df.to_dict(orient="list"))
p = figure(
# title='TSNE Twitter BIO Embeddings',
plot_width=1200,
plot_height=1200,
active_scroll="wheel_zoom",
output_backend="svg",
)
p.add_tools(HoverTool(tooltips="@title"))
p.circle(
source=plot_data,
x="x",
y="y",
line_alpha=0.9,
fill_alpha=0.9,
# size="radius",
fill_color="color",
line_color="color",
)
p.title.text_font_size = value("16pt")
p.xaxis.visible = True
p.yaxis.visible = True
p.background_fill_color = None
p.border_fill_color = None
p.grid.grid_line_color = None
p.outline_line_color = None
# tsne_plot.grid.grid_line_color = None
# tsne_plot.outline_line_color = None
p.toolbar.logo = None
p.toolbar_location = None
export_svg(
p, filename=f"cluster-number{k}.svg", webdriver=driver,
)
export_png(
p, filename=f"cluster-number{k}.png", webdriver=driver,
)
if score > maximum:
maximum = score
ok = k
print(ok)
index_cmap = factor_cmap('cyl_mfr',
palette=Spectral5,
factors=sorted(df.cyl.unique()),
end=1)
p = figure(width=800,
height=300,
title="Mean MPG by # Cylinders and Manufacturer",
x_range=group,
toolbar_location=None,
tooltips=[("MPG", "@mpg_mean"), ("Cyl, Mfr", "@cyl_mfr")])
p.vbar(
x='cyl_mfr',
top='mpg_mean',
width=1,
source=group,
line_color="white",
fill_color=index_cmap,
)
p.y_range.start = 0
p.x_range.range_padding = 0.05
p.xgrid.grid_line_color = None
p.xaxis.axis_label = "Manufacturer grouped by # Cylinders"
p.xaxis.major_label_orientation = 1.2
p.outline_line_color = None
export_svg(p, filename="plot.svg")
def export_as_svg(self, filename):
p = self._tabs.tabs[self._tabs.active].child
self._change_backend_to_svg(p)
export_svg(p, filename=filename)
