-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathAccueil.py
205 lines (184 loc) · 7.02 KB
/
Accueil.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
###############################################################################
# College analysis project
# File: Accueil.py
# Version: 1.0.0
# Date: 2024-08-22
###############################################################################
###############################################################################
# Importing libraries
###############################################################################
import streamlit as st
import pandas as pd
import numpy as np
###############################################################################
# Importing own modules and data
###############################################################################
file_name: str = "fr-en-college-effectifs-niveau-sexe-lv.csv"
file_relative_path: str = "./data/"
logo_path: str = "./img/data_gouv_fr.png"
logo_link: str = "https://www.data.gouv.fr/fr/"
def load_and_cache_data():
"""
Load data from file and cache it in session state for cross-pages access.
"""
data: pd.DataFrame = pd.read_csv(
filepath_or_buffer=file_relative_path + file_name, sep=";"
)
st.session_state["df_init"] = data
def get_regions(data: pd.DataFrame):
regions = data["region_academique"].unique()
return list(regions)
def setup_logo():
lg = f'st.logo(image="{logo_path}", link="{logo_link}", icon_image="{logo_path}")'
st.session_state["logo"] = lg
def display_logo():
st.logo(image=logo_path, link="https://www.data.gouv.fr/fr/", icon_image=logo_path)
###############################################################################
# Main
###############################################################################
def __main__():
# display_logo()
setup_logo()
eval(st.session_state["logo"])
st.title("Effectifs des collèges")
st.header("Description des régions en 2022")
# load data in the session state
load_and_cache_data()
df = st.session_state["df_init"]
df_2022 = df[df["rentree_scolaire"] == 2022]
with st.expander("Description des régions"):
st.dataframe(
df_2022.groupby(["region_academique"])[
[
"nombre_eleves_total",
"6eme_total",
"5eme_total",
"4eme_total",
"3eme_total",
]
]
.sum()
.sort_values(by="nombre_eleves_total", ascending=False)
)
# -------------------------------------------------------------------------
st.subheader("Analyse des genres par niveau")
with st.expander("Description des genres par région"):
st.write(
"Le tableau ci-dessus présente le ratio de filles par niveau par région académique en 2022."
)
df_2022_gender = df_2022.groupby(["region_academique"])[
[
"nombre_eleves_total",
"6eme_total",
"6eme_filles",
"5eme_total",
"5eme_filles",
"4eme_total",
"4eme_filles",
"3eme_total",
"3eme_filles",
]
].sum()
# create the gender ratios for each level by region
df_2022_gender["6eme_ratio"] = (
100 * df_2022_gender["6eme_filles"] / df_2022_gender["6eme_total"]
)
df_2022_gender["5eme_ratio"] = (
100 * df_2022_gender["5eme_filles"] / df_2022_gender["5eme_total"]
)
df_2022_gender["4eme_ratio"] = (
100 * df_2022_gender["4eme_filles"] / df_2022_gender["4eme_total"]
)
df_2022_gender["3eme_ratio"] = (
100 * df_2022_gender["3eme_filles"] / df_2022_gender["3eme_total"]
)
percent_format = st.column_config.NumberColumn(
help="ratio de filles par niveau",
format="%.2f %%",
)
st.dataframe(
data=df_2022_gender[
[
"6eme_ratio",
"5eme_ratio",
"4eme_ratio",
"3eme_ratio",
]
],
column_config={
"6eme_ratio": percent_format,
"5eme_ratio": percent_format,
"4eme_ratio": percent_format,
"3eme_ratio": percent_format,
},
)
# plot this
df_2022_gender.reset_index(inplace=True)
unpivoted_df = pd.melt(
df_2022_gender,
id_vars=["region_academique"], # Columns to keep as identifiers
value_vars=[
"6eme_ratio",
"5eme_ratio",
"4eme_ratio",
"3eme_ratio",
], # Columns to unpivot
var_name="class_level", # Name for the new variable column
value_name="ratio", # Name for the new value column
)
unpivoted_df["niveau"] = (
unpivoted_df["region_academique"] + " - " + unpivoted_df["class_level"]
)
st.dataframe(unpivoted_df[["niveau", "ratio"]])
st.bar_chart(
data=unpivoted_df[["niveau", "ratio"]],
x="niveau",
y="ratio",
y_label="Niveau",
x_label="Ratio de filles (%)",
horizontal=True,
stack=None,
)
# -------------------------------------------------------------------------
st.subheader("Localisation des collèges en 2022")
df_loc = df_2022[["code_postal", "numero_college", "nombre_eleves_total"]]
# Normalize the postal code but keep the 75xxx
df_loc["CP_corrige"] = np.where(
(df_loc["code_postal"] >= 7500) & (df_loc["code_postal"] < 80000),
df_loc["code_postal"],
(df_loc["code_postal"] // 10) * 10,
)
# df_loc["CP_corrige"] = df_loc["code_postal"]
df_loc = df_loc.drop(columns=["code_postal"])
df_loc["numero_college"] = 1
df_loc = (
df_loc.groupby("CP_corrige")[["numero_college", "nombre_eleves_total"]]
.sum()
.reset_index()
)
df_loc.columns = ["code_postal", "nombre_colleges", "nombre_eleves_total"]
# st.dataframe(df_loc)
df_cp_loc = pd.read_csv("./data/CP_centroid.csv")
df_to_map = pd.merge(df_loc, df_cp_loc, on="code_postal")
# create the colors
df_colors = df_2022["region_academique"].drop_duplicates().reset_index()
df_colors = df_colors.drop(columns=["index"])
# df_colors["color"] = np.random.rand(len(df_colors["region_academique"]), 4).tolist()
# set alpha to 0.8
df_colors["color"] = np.hstack(
(
np.random.rand(len(df_colors["region_academique"]), 3),
np.full((len(df_colors["region_academique"]), 1), 0.8),
)
).tolist()
# st.dataframe(df_colors)
df_to_map = df_to_map.merge(
df_2022[["code_postal", "region_academique"]].drop_duplicates(),
on="code_postal",
)
df_to_map = df_to_map.merge(df_colors, on="region_academique")
st.map(data=df_to_map, size="nombre_eleves_total", color="color")
with st.expander("data"):
st.dataframe(df_to_map)
if __name__ == "__main__":
__main__()