-
Notifications
You must be signed in to change notification settings - Fork 2
/
charts.py
305 lines (241 loc) · 11.1 KB
/
charts.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.ticker import MaxNLocator
import yaml
# Robots
with open("web/_data/robots.yml", 'r') as stream:
try:
robots_data = yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
# Projects
with open("web/_data/projects.yml", 'r') as stream:
try:
projects_data = yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
# Youtube
with open("web/_data/youtube.yml", 'r') as stream:
try:
videos_data = yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
# Posts
with open("web/_data/posts.yaml", 'r') as stream:
try:
posts_data = yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
posts_data = posts_data['posts']
# Reviews
with open("web/_data/reviews.yml", 'r') as stream:
try:
reviews_data = yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
# Courses
with open("web/_data/courses.yml", 'r') as stream:
try:
courses_data = yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
def print_raw_stats():
print(f"Robots in the yaml file: {len(robots_data)}")
print(f"Projects in the yaml file: {len(projects_data)}")
print(f"Videos: {len(videos_data)}")
print(f"Posts: {len(posts_data)}")
print(f"Reviews: {len(reviews_data)}")
print(f"Courses: {len(courses_data)}")
robots = pd.DataFrame(robots_data)
projects = pd.DataFrame(projects_data)
videos = pd.DataFrame(videos_data)
posts = pd.DataFrame(posts_data)
reviews = pd.DataFrame(reviews_data)
courses = pd.DataFrame(courses_data)
# Convert dates to datetime
robots['date'] = pd.to_datetime(robots['date'])
projects['date'] = pd.to_datetime(projects['date'])
videos['date'] = pd.to_datetime(videos['published'])
posts['date'] = pd.to_datetime(posts['date'])
reviews['date'] = pd.to_datetime(reviews['date'])
courses['date'] = pd.to_datetime(courses['date_published'])
def produce_courses(year):
# Create a DataFrame for all months of the year
all_months = pd.DataFrame({'Month': pd.date_range(start=f'{year}-01-01', end=f'{year}-12-31', freq='M').strftime('%b')})
courses_filtered = courses[courses['date'].dt.year == year]
monthly_courses = courses_filtered.groupby(courses_filtered['date'].dt.to_period('M'))['name'].agg(['count', lambda x: ', '.join(x)]).reset_index()
# Convert the period index to datetime for easier handling in plotting
monthly_courses['Month'] = monthly_courses['date'].dt.strftime('%b')
# Merge with all_months to include empty months
course_year = pd.merge(all_months, monthly_courses, on='Month', how='left')
course_year['count'] = course_year['count'].fillna(0) # Replace NaN with 0
# Produce the chart
fig, ax = plt.subplots(figsize=(12, 6))
bars = ax.bar(course_year['Month'], course_year['count'])
# Set y-axis to only use whole numbers
ax.yaxis.set_major_locator(MaxNLocator(integer=True))
# Simplify the chart - remove labels, titles, and borders
ax.set_xlabel('')
ax.set_ylabel('')
ax.set_title('')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
# ax.spines['bottom'].set_visible(False)
ax.get_yaxis().set_visible(False)
ax.get_xaxis().set_ticks([])
plt.savefig(f'web/assets/img/course_{year}.png')
# plt.show()
def produce_reviews(year):
# Create a DataFrame for all months of the year
all_months = pd.DataFrame({'Month': pd.date_range(start=f'{year}-01-01', end=f'{year}-12-31', freq='M').strftime('%b')})
reviews_filtered = reviews[reviews['date'].dt.year == year]
monthly_reviews = reviews_filtered.groupby(reviews_filtered['date'].dt.to_period('M'))['title'].agg(['count', lambda x: ', '.join(x)]).reset_index()
# Convert the period index to datetime for easier handling in plotting
monthly_reviews['Month'] = monthly_reviews['date'].dt.strftime('%b')
# Merge with all_months to include empty months
review_year = pd.merge(all_months, monthly_reviews, on='Month', how='left')
review_year['count'] = review_year['count'].fillna(0) # Replace NaN with 0
# Produce the chart
fig, ax = plt.subplots(figsize=(12, 6))
bars = ax.bar(review_year['Month'], review_year['count'])
# Set y-axis to only use whole numbers
ax.yaxis.set_major_locator(MaxNLocator(integer=True))
# Simplify the chart - remove labels, titles, and borders
ax.set_xlabel('')
ax.set_ylabel('')
ax.set_title('')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
# ax.spines['bottom'].set_visible(False)
ax.get_yaxis().set_visible(False)
ax.get_xaxis().set_ticks([])
plt.savefig(f'web/assets/img/reviews_{year}.png')
# plt.show()
def produce_posts(year):
# Create a DataFrame for all months of the year
all_months = pd.DataFrame({'Month': pd.date_range(start=f'{year}-01-01', end=f'{year}-12-31', freq='M').strftime('%b')})
posts_filtered = posts[posts['date'].dt.year == year]
monthly_posts = posts_filtered.groupby(posts_filtered['date'].dt.to_period('M'))['title'].agg(['count', lambda x: ', '.join(x)]).reset_index()
# Convert the period index to datetime for easier handling in plotting
monthly_posts['Month'] = monthly_posts['date'].dt.strftime('%b')
# Merge with all_months to include empty months
posts_year = pd.merge(all_months, monthly_posts, on='Month', how='left')
posts_year['count'] = posts_year['count'].fillna(0) # Replace NaN with 0
# Produce the chart
fig, ax = plt.subplots(figsize=(12, 6))
bars = ax.bar(posts_year['Month'], posts_year['count'])
# Set y-axis to only use whole numbers
ax.yaxis.set_major_locator(MaxNLocator(integer=True))
# Simplify the chart - remove labels, titles, and borders
ax.set_xlabel('')
ax.set_ylabel('')
ax.set_title('')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
# ax.spines['bottom'].set_visible(False)
ax.get_yaxis().set_visible(False)
ax.get_xaxis().set_ticks([])
plt.savefig(f'web/assets/img/posts_{year}.png')
# plt.show()
def produce_projects(year):
# Create a DataFrame for all months of the year
all_months = pd.DataFrame({'Month': pd.date_range(start=f'{year}-01-01', end=f'{year}-12-31', freq='M').strftime('%b')})
projects_filtered = projects[projects['date'].dt.year == year]
monthly_projects = projects_filtered.groupby(projects_filtered['date'].dt.to_period('M'))['name'].agg(['count', lambda x: ', '.join(x)]).reset_index()
# Convert the period index to datetime for easier handling in plotting
monthly_projects['Month'] = monthly_projects['date'].dt.strftime('%b')
# Merge with all_months to include empty months
projects_year = pd.merge(all_months, monthly_projects, on='Month', how='left')
projects_year['count'] = projects_year['count'].fillna(0) # Replace NaN with 0
# Produce the chart
fig, ax = plt.subplots(figsize=(12, 6))
bars = ax.bar(projects_year['Month'], projects_year['count'])
# Set y-axis to only use whole numbers
ax.yaxis.set_major_locator(MaxNLocator(integer=True))
# Simplify the chart - remove labels, titles, and borders
ax.set_xlabel('')
ax.set_ylabel('')
ax.set_title('')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
# ax.spines['bottom'].set_visible(False)
ax.get_yaxis().set_visible(False)
ax.get_xaxis().set_ticks([])
plt.savefig(f'web/assets/img/projects_{year}.png')
# plt.show()
def produce_videos(year):
# Create a DataFrame for all months of the year
all_months = pd.DataFrame({'Month': pd.date_range(start=f'{year}-01-01', end=f'{year}-12-31', freq='M').strftime('%b')})
videos_filtered = videos[videos['date'].dt.year == year]
monthly_videos = videos_filtered.groupby(videos_filtered['date'].dt.to_period('M'))['title'].agg(['count', lambda x: ', '.join(x)]).reset_index()
# Convert the period index to datetime for easier handling in plotting
monthly_videos['Month'] = monthly_videos['date'].dt.strftime('%b')
# Merge with all_months to include empty months
videos_year = pd.merge(all_months, monthly_videos, on='Month', how='left')
videos_year['count'] = videos_year['count'].fillna(0) # Replace NaN with 0
# Produce the chart
fig, ax = plt.subplots(figsize=(12, 6))
bars = ax.bar(videos_year['Month'], videos_year['count'])
# Set y-axis to only use whole numbers
ax.yaxis.set_major_locator(MaxNLocator(integer=True))
# Simplify the chart - remove labels, titles, and borders
ax.set_xlabel('')
ax.set_ylabel('')
ax.set_title('')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
# ax.spines['bottom'].set_visible(False)
ax.get_yaxis().set_visible(False)
ax.get_xaxis().set_ticks([])
plt.savefig(f'web/assets/img/videos_{year}.png')
# plt.show()
def produce_charts(year):
produce_robots(year)
produce_projects(year)
produce_videos(year)
produce_posts(year)
produce_reviews(year)
produce_courses(year)
print_raw_stats()
def produce_robots(year):
# Create a DataFrame for all months of the year
all_months = pd.DataFrame({'Month': pd.date_range(start=f'{year}-01-01', end=f'{year}-12-31', freq='M').strftime('%b')})
robots_filtered = robots[robots['date'].dt.year == year]
monthly_robots = robots_filtered.groupby(robots_filtered['date'].dt.to_period('M'))['name'].agg(['count', lambda x: ', '.join(x)]).reset_index()
# Convert the period index to datetime for easier handling in plotting
monthly_robots['Month'] = monthly_robots['date'].dt.strftime('%b')
# Merge with all_months to include empty months
robots_year = pd.merge(all_months, monthly_robots, on='Month', how='left')
robots_year['count'] = robots_year['count'].fillna(0) # Replace NaN with 0
# Produce the chart
fig, ax = plt.subplots(figsize=(12, 6))
bars = ax.bar(robots_year['Month'], robots_year['count'])
# Set y-axis to only use whole numbers
ax.yaxis.set_major_locator(MaxNLocator(integer=True))
# Simplify the chart - remove labels, titles, and borders
ax.set_xlabel('')
ax.set_ylabel('')
ax.set_title('')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
# ax.spines['bottom'].set_visible(False)
ax.get_yaxis().set_visible(False)
ax.get_xaxis().set_ticks([])
plt.savefig(f'web/assets/img/robots_{year}.png')
# plt.show()
def monthly_stats(year):
robots_filtered = robots[robots['date'].dt.year == year]
monthly_robots = robots_filtered.groupby(robots_filtered['date'].dt.to_period('M'))['name'].agg(['count',lambda x: ', '.join(x)])
print(monthly_robots)
# monthly_stats(2023)
produce_charts(2020)
produce_charts(2021)
produce_charts(2022)
produce_charts(2023)
produce_charts(2024)