update app.py
Browse files- app.py +282 -226
- requirements.txt +5 -0
app.py
CHANGED
@@ -1,8 +1,13 @@
|
|
1 |
import json
|
2 |
|
3 |
import altair as alt
|
|
|
|
|
|
|
4 |
import pandas as pd
|
5 |
import streamlit as st
|
|
|
|
|
6 |
|
7 |
|
8 |
def read_json(file_name):
|
@@ -11,256 +16,307 @@ def read_json(file_name):
|
|
11 |
return json_data
|
12 |
|
13 |
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
df = df[
|
21 |
-
[
|
22 |
-
"project_name",
|
23 |
-
"description",
|
24 |
-
"url",
|
25 |
-
"stargazers_count",
|
26 |
-
"downloads",
|
27 |
-
"source",
|
28 |
-
"score",
|
29 |
-
"first_commit",
|
30 |
-
"latest_commit",
|
31 |
-
"languages",
|
32 |
-
"model_or_dataset",
|
33 |
-
]
|
34 |
-
]
|
35 |
-
df = df.sort_values(by="score", ascending=False)
|
36 |
-
|
37 |
-
|
38 |
-
# Convert DataFrame for Dashboard
|
39 |
-
df["first_commit"] = pd.to_datetime(df["first_commit"], errors="coerce")
|
40 |
-
df["latest_commit"] = pd.to_datetime(df["latest_commit"], errors="coerce")
|
41 |
-
df["activity_period"] = (df["latest_commit"] - df["first_commit"]).dt.days
|
42 |
-
df = df[df["first_commit"] >= "2009-01-01"]
|
43 |
-
df = df[df["latest_commit"] >= "2009-01-01"]
|
44 |
-
df["str_languages"] = df["languages"].apply(
|
45 |
-
lambda x: ",".join(x) if isinstance(x, list) else str(x)
|
46 |
-
)
|
47 |
-
df["year"] = df["first_commit"].dt.year
|
48 |
-
|
49 |
-
|
50 |
-
# Set streamlit page settings
|
51 |
-
title = "Awesome Japanese NLP resources Dashboard"
|
52 |
-
icon = "π"
|
53 |
-
|
54 |
-
st.set_page_config(
|
55 |
-
page_title=title,
|
56 |
-
page_icon=icon,
|
57 |
-
layout="wide",
|
58 |
-
initial_sidebar_state="expanded",
|
59 |
-
)
|
60 |
-
|
61 |
-
# Main streamlit page (sidebar)
|
62 |
-
alt.themes.enable("dark")
|
63 |
-
with st.sidebar:
|
64 |
-
st.title(f"{title} {icon}")
|
65 |
-
st.markdown(
|
66 |
-
"You can search for open-source software from [1250+ Japanese NLP repositories](https://github.com/taishi-i/awesome-japanese-nlp-resources)."
|
67 |
-
)
|
68 |
-
query = st.text_input(label="Search keyword")
|
69 |
|
70 |
-
|
71 |
-
|
72 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
)
|
|
|
74 |
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
if selected_source_type == "GitHub":
|
79 |
-
selected_model_or_dataset = None
|
80 |
-
all_languages = (
|
81 |
-
df["languages"]
|
82 |
-
.dropna()
|
83 |
-
.apply(lambda x: x if isinstance(x, list) else [])
|
84 |
-
.explode()
|
85 |
-
.unique()
|
86 |
-
)
|
87 |
-
all_languages = [""] + all_languages.tolist()
|
88 |
-
selected_languges = st.selectbox(
|
89 |
-
"Choose a programming language", all_languages, index=0
|
90 |
-
)
|
91 |
-
|
92 |
-
min_stars = int(df["stargazers_count"].min())
|
93 |
-
max_stars = int(df["stargazers_count"].max())
|
94 |
-
|
95 |
-
stars_range = st.slider(
|
96 |
-
"Choose the range for the stargazer count",
|
97 |
-
min_value=min_stars,
|
98 |
-
max_value=max_stars,
|
99 |
-
value=(min_stars, max_stars),
|
100 |
-
)
|
101 |
-
else:
|
102 |
-
selected_languges = None
|
103 |
-
selected_model_or_dataset = st.selectbox(
|
104 |
-
"Choose a model or a dataset", ["", "model", "dataset"], index=0
|
105 |
-
)
|
106 |
|
107 |
-
|
108 |
-
|
|
|
|
|
|
|
|
|
|
|
109 |
|
110 |
-
|
111 |
-
|
112 |
-
min_value=min_downloads,
|
113 |
-
max_value=max_downloads,
|
114 |
-
value=(min_downloads, max_downloads),
|
115 |
-
)
|
116 |
|
117 |
-
min_activity_period = int(df["activity_period"].min())
|
118 |
-
max_activity_period = int(df["activity_period"].max())
|
119 |
|
120 |
-
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
value=(min_activity_period, max_activity_period),
|
125 |
-
)
|
126 |
-
years = sorted(list(set(df["year"].dropna().astype(int).tolist())))
|
127 |
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
|
|
|
|
|
|
|
|
|
135 |
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
140 |
|
|
|
|
|
|
|
|
|
|
|
|
|
141 |
|
142 |
-
if selected_source_type == "GitHub":
|
143 |
-
df = df[
|
144 |
-
(df["stargazers_count"] >= stars_range[0])
|
145 |
-
& (df["stargazers_count"] <= stars_range[1])
|
146 |
-
]
|
147 |
-
else:
|
148 |
df = df[
|
149 |
-
(df["
|
150 |
-
& (df["
|
151 |
]
|
152 |
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
]
|
157 |
-
|
158 |
-
|
159 |
-
|
160 |
-
)
|
161 |
-
|
162 |
-
|
163 |
-
)
|
164 |
-
df = df[contained_description | contained_project_name]
|
165 |
-
|
166 |
-
if selected_languges:
|
167 |
-
df = df[
|
168 |
-
df["str_languages"].str.contains(
|
169 |
-
selected_languges, case=False, na=False
|
170 |
-
)
|
171 |
-
]
|
172 |
|
173 |
-
if selected_model_or_dataset:
|
174 |
df = df[
|
175 |
-
df["
|
176 |
-
|
177 |
-
)
|
178 |
]
|
179 |
|
180 |
-
|
181 |
-
|
182 |
-
col1, col2 = st.columns(2, gap="large")
|
183 |
-
|
184 |
-
with col1:
|
185 |
-
st.markdown("### DataFrame")
|
186 |
-
st.markdown(f"#### Number of repositories: {len(df)}")
|
187 |
-
st.dataframe(df, height=600)
|
188 |
-
|
189 |
-
projects_per_year = (
|
190 |
-
df.groupby("year").size().reset_index(name="project_count")
|
191 |
)
|
192 |
-
|
193 |
-
|
194 |
-
alt.Chart(projects_per_year)
|
195 |
-
.mark_bar()
|
196 |
-
.encode(
|
197 |
-
x=alt.X("year:O", title="Year"),
|
198 |
-
y=alt.Y("project_count:Q", title="Number of repositories"),
|
199 |
-
tooltip=["year", "project_count"],
|
200 |
-
)
|
201 |
-
.properties(
|
202 |
-
title="Number of projects per year based on the uear of the first commit",
|
203 |
-
width=600,
|
204 |
-
height=400,
|
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 |
-
st.markdown(f"### Activity period vs {vs_type}")
|
249 |
-
chart = (
|
250 |
-
alt.Chart(df)
|
251 |
-
.mark_circle(size=60)
|
252 |
-
.encode(
|
253 |
-
x=alt.X("activity_period:Q", title="Activity Period (Days)"),
|
254 |
-
y=alt.Y(f"{vs_type}:Q", title=f"{vs_type}"),
|
255 |
-
tooltip=[
|
256 |
-
"project_name",
|
257 |
-
"activity_period",
|
258 |
-
f"{vs_type}",
|
259 |
-
],
|
260 |
)
|
261 |
-
|
262 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
263 |
)
|
264 |
-
|
265 |
-
|
266 |
-
|
|
|
|
|
|
|
|
1 |
import json
|
2 |
|
3 |
import altair as alt
|
4 |
+
import japanize_matplotlib
|
5 |
+
import matplotlib.pyplot as plt
|
6 |
+
import nagisa
|
7 |
import pandas as pd
|
8 |
import streamlit as st
|
9 |
+
from datasets import load_dataset
|
10 |
+
from wordcloud import WordCloud
|
11 |
|
12 |
|
13 |
def read_json(file_name):
|
|
|
16 |
return json_data
|
17 |
|
18 |
|
19 |
+
@st.cache_data
|
20 |
+
def convert_to_dataframe():
|
21 |
+
# Load a json file
|
22 |
+
json_file = "awesome-japanese-nlp-resources-search.json"
|
23 |
+
json_data = read_json(json_file)
|
24 |
+
df = pd.DataFrame(json_data)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
|
26 |
+
# Sorted by selected columns
|
27 |
+
df = df[
|
28 |
+
[
|
29 |
+
"project_name",
|
30 |
+
"description",
|
31 |
+
"url",
|
32 |
+
"stargazers_count",
|
33 |
+
"downloads",
|
34 |
+
"source",
|
35 |
+
"score",
|
36 |
+
"first_commit",
|
37 |
+
"latest_commit",
|
38 |
+
"languages",
|
39 |
+
"model_or_dataset",
|
40 |
+
]
|
41 |
+
]
|
42 |
+
df = df.sort_values(by="score", ascending=False)
|
43 |
+
|
44 |
+
# Convert DataFrame for Dashboard
|
45 |
+
df["first_commit"] = pd.to_datetime(df["first_commit"], errors="coerce")
|
46 |
+
df["latest_commit"] = pd.to_datetime(df["latest_commit"], errors="coerce")
|
47 |
+
df["activity_period"] = (df["latest_commit"] - df["first_commit"]).dt.days
|
48 |
+
df = df[df["first_commit"] >= "2009-01-01"]
|
49 |
+
df = df[df["latest_commit"] >= "2009-01-01"]
|
50 |
+
df["str_languages"] = df["languages"].apply(
|
51 |
+
lambda x: ",".join(x) if isinstance(x, list) else str(x)
|
52 |
)
|
53 |
+
df["year"] = df["first_commit"].dt.year
|
54 |
|
55 |
+
dataset = load_dataset("taishi-i/nagisa_stopwords")
|
56 |
+
stopwords = dataset["nagisa_stopwords"]["words"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
|
58 |
+
def tokenize_description(description):
|
59 |
+
tokens = nagisa.filter(description, filter_postags=["ε©θ©", "ε©εθ©"])
|
60 |
+
words = tokens.words
|
61 |
+
words = [word for word in words if len(word.strip()) > 0]
|
62 |
+
words = [word for word in words if word not in stopwords]
|
63 |
+
words = " ".join(words)
|
64 |
+
return words
|
65 |
|
66 |
+
df["tokenized_description"] = df["description"].apply(tokenize_description)
|
67 |
+
return df
|
|
|
|
|
|
|
|
|
68 |
|
|
|
|
|
69 |
|
70 |
+
def main():
|
71 |
+
# Set streamlit page settings
|
72 |
+
title = "Awesome Japanese NLP resources Dashboard"
|
73 |
+
icon = "π"
|
|
|
|
|
|
|
74 |
|
75 |
+
st.set_page_config(
|
76 |
+
page_title=title,
|
77 |
+
page_icon=icon,
|
78 |
+
layout="wide",
|
79 |
+
initial_sidebar_state="expanded",
|
80 |
)
|
81 |
+
df = convert_to_dataframe()
|
82 |
+
|
83 |
+
# Main streamlit page (sidebar)
|
84 |
+
alt.themes.enable("dark")
|
85 |
+
with st.sidebar:
|
86 |
+
st.title(f"{title} {icon}")
|
87 |
+
st.markdown(
|
88 |
+
"You can search for open-source software from [1250+ Japanese NLP repositories](https://github.com/taishi-i/awesome-japanese-nlp-resources)."
|
89 |
+
)
|
90 |
+
query = st.text_input(label="Search keyword")
|
91 |
|
92 |
+
source_type = ["GitHub", "Hugging Face"]
|
93 |
+
selected_source_type = st.selectbox(
|
94 |
+
"Choose a source type: GitHub or Hugging Face", source_type
|
95 |
+
)
|
96 |
|
97 |
+
# Filtering GitHub or Hugging Face
|
98 |
+
df = df[df["source"] == selected_source_type]
|
99 |
+
|
100 |
+
if selected_source_type == "GitHub":
|
101 |
+
selected_model_or_dataset = None
|
102 |
+
all_languages = (
|
103 |
+
df["languages"]
|
104 |
+
.dropna()
|
105 |
+
.apply(lambda x: x if isinstance(x, list) else [])
|
106 |
+
.explode()
|
107 |
+
.unique()
|
108 |
+
)
|
109 |
+
all_languages = [""] + all_languages.tolist()
|
110 |
+
selected_languges = st.selectbox(
|
111 |
+
"Choose a programming language", all_languages, index=0
|
112 |
+
)
|
113 |
+
|
114 |
+
min_stars = int(df["stargazers_count"].min())
|
115 |
+
max_stars = int(df["stargazers_count"].max())
|
116 |
+
|
117 |
+
stars_range = st.slider(
|
118 |
+
"Choose the range for the stargazer count",
|
119 |
+
min_value=min_stars,
|
120 |
+
max_value=max_stars,
|
121 |
+
value=(min_stars, max_stars),
|
122 |
+
)
|
123 |
+
else:
|
124 |
+
selected_languges = None
|
125 |
+
selected_model_or_dataset = st.selectbox(
|
126 |
+
"Choose a model or a dataset",
|
127 |
+
["", "model", "dataset"],
|
128 |
+
index=0,
|
129 |
+
)
|
130 |
+
|
131 |
+
min_downloads = int(df["downloads"].min())
|
132 |
+
max_downloads = int(df["downloads"].max())
|
133 |
+
|
134 |
+
downloads_range = st.slider(
|
135 |
+
"Choose the range for the number of downloads",
|
136 |
+
min_value=min_downloads,
|
137 |
+
max_value=max_downloads,
|
138 |
+
value=(min_downloads, max_downloads),
|
139 |
+
)
|
140 |
+
|
141 |
+
min_activity_period = int(df["activity_period"].min())
|
142 |
+
max_activity_period = int(df["activity_period"].max())
|
143 |
+
|
144 |
+
activity_period_range = st.slider(
|
145 |
+
"Select the range for activity periods (in days)",
|
146 |
+
min_value=min_activity_period,
|
147 |
+
max_value=max_activity_period,
|
148 |
+
value=(min_activity_period, max_activity_period),
|
149 |
+
)
|
150 |
+
years = sorted(list(set(df["year"].dropna().astype(int).tolist())))
|
151 |
|
152 |
+
selected_year_range = st.slider(
|
153 |
+
"Select a range for the years of the first commit",
|
154 |
+
min_value=min(years),
|
155 |
+
max_value=max(years),
|
156 |
+
value=(min(years), max(years)),
|
157 |
+
)
|
158 |
|
|
|
|
|
|
|
|
|
|
|
|
|
159 |
df = df[
|
160 |
+
(df["year"] >= selected_year_range[0])
|
161 |
+
& (df["year"] <= selected_year_range[1])
|
162 |
]
|
163 |
|
164 |
+
if selected_source_type == "GitHub":
|
165 |
+
df = df[
|
166 |
+
(df["stargazers_count"] >= stars_range[0])
|
167 |
+
& (df["stargazers_count"] <= stars_range[1])
|
168 |
+
]
|
169 |
+
else:
|
170 |
+
df = df[
|
171 |
+
(df["downloads"] >= downloads_range[0])
|
172 |
+
& (df["downloads"] <= downloads_range[1])
|
173 |
+
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
174 |
|
|
|
175 |
df = df[
|
176 |
+
(df["activity_period"] >= activity_period_range[0])
|
177 |
+
& (df["activity_period"] <= activity_period_range[1])
|
|
|
178 |
]
|
179 |
|
180 |
+
contained_description = df["description"].str.contains(
|
181 |
+
query, case=False, na=False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
182 |
)
|
183 |
+
contained_project_name = df["project_name"].str.contains(
|
184 |
+
query, case=False, na=False
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
185 |
)
|
186 |
+
df = df[contained_description | contained_project_name]
|
187 |
+
|
188 |
+
if selected_languges:
|
189 |
+
df = df[
|
190 |
+
df["str_languages"].str.contains(
|
191 |
+
selected_languges, case=False, na=False
|
192 |
+
)
|
193 |
+
]
|
194 |
+
|
195 |
+
if selected_model_or_dataset:
|
196 |
+
df = df[
|
197 |
+
df["model_or_dataset"].str.contains(
|
198 |
+
selected_model_or_dataset, case=False, na=False
|
199 |
+
)
|
200 |
+
]
|
201 |
+
|
202 |
+
# Main streamlit page (columns)
|
203 |
+
col1, col2 = st.columns(2, gap="large")
|
204 |
+
|
205 |
+
with col1:
|
206 |
+
st.markdown("### DataFrame")
|
207 |
+
st.markdown(f"#### Number of repositories: {len(df)}")
|
208 |
+
if selected_source_type == "GitHub":
|
209 |
+
stats_key = "stargazers_count"
|
210 |
+
else:
|
211 |
+
stats_key = "downloads"
|
212 |
+
|
213 |
+
if len(df) > 0:
|
214 |
+
mean_value = int(df[stats_key].mean())
|
215 |
+
min_value = int(df[stats_key].min())
|
216 |
+
max_value = int(df[stats_key].max())
|
217 |
+
st.markdown(
|
218 |
+
f"#### {stats_key} mean: {int(mean_value)}, min: {min_value}, max: {max_value}"
|
219 |
+
)
|
220 |
+
|
221 |
+
st.dataframe(df, height=600)
|
222 |
+
|
223 |
+
if len(df) > 0:
|
224 |
+
st.markdown("### Word Cloud")
|
225 |
+
descriptions = df["tokenized_description"].tolist()
|
226 |
+
combined_text = " ".join(descriptions)
|
227 |
+
|
228 |
+
wordcloud = WordCloud(
|
229 |
+
width=800,
|
230 |
+
height=400,
|
231 |
+
font_path=japanize_matplotlib.get_font_ttf_path(),
|
232 |
+
max_words=50,
|
233 |
+
colormap="PuBu",
|
234 |
+
).generate(combined_text)
|
235 |
+
|
236 |
+
fig, ax = plt.subplots()
|
237 |
+
ax.imshow(wordcloud, interpolation="bilinear")
|
238 |
+
ax.axis("off")
|
239 |
+
st.pyplot(fig, use_container_width=True)
|
240 |
+
|
241 |
+
with col2:
|
242 |
+
if selected_source_type == "GitHub":
|
243 |
+
vs_type = "stargazers_count"
|
244 |
+
else:
|
245 |
+
vs_type = "downloads"
|
246 |
+
|
247 |
+
st.markdown(f"### First commit vs {vs_type}")
|
248 |
+
chart = (
|
249 |
+
alt.Chart(df)
|
250 |
+
.mark_circle(size=60)
|
251 |
+
.encode(
|
252 |
+
x="first_commit:T",
|
253 |
+
y=f"{vs_type}:Q",
|
254 |
+
tooltip=["first_commit", "project_name", f"{vs_type}"],
|
255 |
+
)
|
256 |
+
.properties(
|
257 |
+
title=f"Relationship between first commit date and {vs_type}",
|
258 |
+
)
|
259 |
+
.interactive()
|
260 |
)
|
261 |
+
st.altair_chart(chart, use_container_width=True)
|
262 |
+
|
263 |
+
st.markdown(f"### Latest commit vs {vs_type}")
|
264 |
+
chart = (
|
265 |
+
alt.Chart(df)
|
266 |
+
.mark_circle(size=60)
|
267 |
+
.encode(
|
268 |
+
x="latest_commit:T",
|
269 |
+
y=f"{vs_type}:Q",
|
270 |
+
tooltip=["project_name", "latest_commit", f"{vs_type}"],
|
271 |
+
)
|
272 |
+
.properties(
|
273 |
+
title=f"Relationship between latest commit date and {vs_type}",
|
274 |
+
)
|
275 |
+
.interactive()
|
276 |
)
|
277 |
+
st.altair_chart(chart, use_container_width=True)
|
278 |
+
|
279 |
+
st.markdown(f"### Activity period vs {vs_type}")
|
280 |
+
chart = (
|
281 |
+
alt.Chart(df)
|
282 |
+
.mark_circle(size=60)
|
283 |
+
.encode(
|
284 |
+
x=alt.X("activity_period:Q", title="Activity Period (Days)"),
|
285 |
+
y=alt.Y(f"{vs_type}:Q", title=f"{vs_type}"),
|
286 |
+
tooltip=[
|
287 |
+
"project_name",
|
288 |
+
"activity_period",
|
289 |
+
f"{vs_type}",
|
290 |
+
],
|
291 |
+
)
|
292 |
+
.properties(
|
293 |
+
title=f"Relationship between activity period and {vs_type}",
|
294 |
+
)
|
295 |
+
.interactive()
|
296 |
)
|
297 |
+
st.altair_chart(chart, use_container_width=True)
|
298 |
+
|
299 |
+
projects_per_year = (
|
300 |
+
df.groupby("year").size().reset_index(name="project_count")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
301 |
)
|
302 |
+
|
303 |
+
chart = (
|
304 |
+
alt.Chart(projects_per_year)
|
305 |
+
.mark_bar()
|
306 |
+
.encode(
|
307 |
+
x=alt.X("year:O", title="Year"),
|
308 |
+
y=alt.Y("project_count:Q", title="Number of repositories"),
|
309 |
+
tooltip=["year", "project_count"],
|
310 |
+
)
|
311 |
+
.properties(
|
312 |
+
title="Number of projects per year based on the uear of the first commit",
|
313 |
+
width=600,
|
314 |
+
height=400,
|
315 |
+
)
|
316 |
)
|
317 |
+
|
318 |
+
st.altair_chart(chart, use_container_width=True)
|
319 |
+
|
320 |
+
|
321 |
+
if __name__ == "__main__":
|
322 |
+
main()
|
requirements.txt
CHANGED
@@ -2,3 +2,8 @@ streamlit
|
|
2 |
pandas
|
3 |
altair
|
4 |
plotly
|
|
|
|
|
|
|
|
|
|
|
|
2 |
pandas
|
3 |
altair
|
4 |
plotly
|
5 |
+
matplotlib
|
6 |
+
nagisa
|
7 |
+
datasets
|
8 |
+
wordcloud
|
9 |
+
japanize_matplotlib
|