Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

UP my solution #157

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

UP my solution #157

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
46b38c6
UP my solution
Maryem-HAJJI Dec 21, 2023
4fcf0a6
2 commit
Maryem-HAJJI Dec 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 28 additions & 10 deletions pandas_questions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,9 +15,9 @@

def load_data():
"""Load data from the CSV files referundum/regions/departments."""
referendum = pd.DataFrame({})
regions = pd.DataFrame({})
departments = pd.DataFrame({})
referendum = pd.read_csv('./data/referendum.csv', sep=';')
regions = pd.read_csv('./data/regions.csv', sep=',')
departments = pd.read_csv('./data/departments.csv', sep=',')

return referendum, regions, departments

Expand All @@ -28,8 +28,11 @@ def merge_regions_and_departments(regions, departments):
The columns in the final DataFrame should be:
['code_reg', 'name_reg', 'code_dep', 'name_dep']
"""

return pd.DataFrame({})
df = regions.merge(departments, left_on='code',
right_on='region_code',
suffixes=('_reg', '_dep'))
df = df[['code_reg', 'name_reg', 'code_dep', 'name_dep']]
return df


def merge_referendum_and_areas(referendum, regions_and_departments):
Expand All @@ -38,8 +41,15 @@ def merge_referendum_and_areas(referendum, regions_and_departments):
You can drop the lines relative to DOM-TOM-COM departments, and the
french living abroad.
"""
filtered_referendum = referendum[
~referendum['Department code'].str.startswith('Z')]
filtered_referendum.loc[:, 'Department code'] = filtered_referendum[
'Department code'].apply(lambda x: str(x).zfill(2))
merged_dataframe = filtered_referendum.merge(regions_and_departments,
left_on='Department code',
right_on='code_dep')

return pd.DataFrame({})
return merged_dataframe


def compute_referendum_result_by_regions(referendum_and_areas):
Expand All @@ -48,8 +58,12 @@ def compute_referendum_result_by_regions(referendum_and_areas):
The return DataFrame should be indexed by `code_reg` and have columns:
['name_reg', 'Registered', 'Abstentions', 'Null', 'Choice A', 'Choice B']
"""

return pd.DataFrame({})
df = referendum_and_areas.groupby([
'code_reg', 'name_reg']).sum().reset_index()
df = df.set_index('code_reg')[['name_reg',
'Registered', 'Abstentions',
'Null', 'Choice A', 'Choice B']]
return df


def plot_referendum_map(referendum_result_by_regions):
Expand All @@ -61,8 +75,12 @@ def plot_referendum_map(referendum_result_by_regions):
should display the rate of 'Choice A' over all expressed ballots.
* Return a gpd.GeoDataFrame with a column 'ratio' containing the results.
"""

return gpd.GeoDataFrame({})
geo_data = gpd.read_file('data/regions.geojson')
df = pd.merge(geo_data, referendum_result_by_regions, left_on='code',
right_index=True, how='left')
df['ratio'] = df['Choice A'] / (df['Choice A'] + df['Choice B'])
df.plot(column='ratio', legend=True)
return gpd.GeoDataFrame(df)


if __name__ == "__main__":
Expand Down
Loading