Dabidou025

.github/workflows/python-app.yml

@@ -42,9 +42,7 @@ jobs:
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=80 --statistics
+        flake8 . --count --max-complexity=10 --max-line-length=80 --statistics
     - name: Check doc style with pydocstyle
       run: pydocstyle
 

README.md

@@ -1,4 +1,4 @@
-# Assignment 2 for the DataCamp course X-DataScience Master
+# Assignment 2 for the DataCamp course X-DataScience Master - pandas
 
 ## What we want you to learn by doing this assignment:
 
@@ -10,11 +10,16 @@
 
 ## How?
 
-  - For the repository by clicking on the `Fork` button on the upper right corner
+  - Fork the repository by clicking on the `Fork` button on the upper right corner
   - Clone the repository of your fork with: `git clone https://github.com/MYLOGIN/datacamp-assignment-pandas` (replace MYLOGIN with your GitHub login)
-  - Create a branch called `myassignment` using `git checkout -b myassignment`
+  - Create a branch called `MYLOGIN` using `git checkout -b MYLOGIN`
   - Make the changes to complete the assignment. You have to modify the files that contain `questions` in their name. Do not modify the files that start with `test_`.
-  - Open the pull request on GitHub
+  - Check locally that your solution meet the test by running `pytest` from the root of the repo. You may need to install `pytest` using `pip` or `conda`.
+  - Check the code formating for your solution using `flake8`. You may need to install `flake8` using `pip` or `conda`.
+  - Open the pull request on GitHub:
+     - Create a commit with `git add -u` and `git commit -m "UP my solution"`
+     - Push your branch on your fork: `git push -u origin MYLOGIN`
+     - Go to your repo in your browser and click the `Open a PR` button.
   - Keep pushing to your branch until the continuous integration system is green.
   - When it is green notify the professors on Slack that your done.
 

pandas_questions.py

@@ -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
 
@@ -29,7 +29,14 @@ def merge_regions_and_departments(regions, departments):
     ['code_reg', 'name_reg', 'code_dep', 'name_dep']
     """
 
-    return pd.DataFrame({})
+    df = departments.merge(regions, left_on='region_code', right_on='code')
+    df = df[['region_code','name_y','code_x','name_x']]
+    df = df.rename(columns={'region_code': 'code_reg',
+                            'name_y': 'name_reg',
+                            'code_x': 'code_dep',
+                            'name_x': 'name_dep'})
+
+    return df
 
 
 def merge_referendum_and_areas(referendum, regions_and_departments):
@@ -38,8 +45,10 @@ 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.
     """
+    referendum["Department code"] = referendum["Department code"].str.zfill(2)
+    df = pd.merge(regions_and_departments, referendum, left_on='code_dep', right_on='Department code', how='inner')
 
-    return pd.DataFrame({})
+    return df
 
 
 def compute_referendum_result_by_regions(referendum_and_areas):
@@ -49,20 +58,35 @@ def compute_referendum_result_by_regions(referendum_and_areas):
     ['name_reg', 'Registered', 'Abstentions', 'Null', 'Choice A', 'Choice B']
     """
 
-    return pd.DataFrame({})
+    df = referendum_and_areas.groupby(['name_reg', 'code_reg'], as_index=False).agg('sum')
+    df = df.drop('Town code', axis=1)
+    df = df.set_index("code_reg")
+
+    return df
 
 
-def plot_referendum_map(referendum_result_by_region):
+def plot_referendum_map(referendum_result_by_regions):
     """Plot a map with the results from the referendum.
 
     * Load the geographic data with geopandas from `regions.geojson`.
-    * Merge these info in `referendum_and_areas`.
+    * Merge these info into `referendum_result_by_regions`.
     * Use the method `GeoDataFrame.plot` to display the result map. The results
       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_reg = gpd.read_file('data/regions.geojson')
+    geo_referundum = geo_reg.merge(referendum_result_by_regions, 
+                                    left_on='code', right_on='code_reg',
+                                    how='inner')
+    geo_referundum['ratio'] = geo_referundum['Choice A'] / (geo_referundum['Registered'] -
+                                geo_referundum['Abstentions'] -
+                                geo_referundum['Null'])
+
+    geo_referundum.rename({'nom': 'name_reg'})
+    geo_referundum.plot(column='ratio', legend=True,
+                        legend_kwds={'label': "choice_A_ratio",
+                                     'orientation': "horizontal"})
+    return geo_referundum
 
 
 if __name__ == "__main__":

requirements.txt

@@ -2,3 +2,4 @@ numpy
 pandas
 pytest
 geopandas
+descartes

test_pandas_questions.py

@@ -69,29 +69,29 @@ def test_compute_referendum_result_by_regions():
     referendum_and_areas = merge_referendum_and_areas(
         referendum, regions_and_departments
     )
-    referendum_result_by_region = compute_referendum_result_by_regions(
+    referendum_result_by_regions = compute_referendum_result_by_regions(
         referendum_and_areas
     )
 
     # Check result shape
-    assert set(referendum_result_by_region.columns) == set([
+    assert set(referendum_result_by_regions.columns) == set([
         'name_reg', 'Registered', 'Abstentions', 'Null', 'Choice A', 'Choice B'
     ]), (
         'To keep the name of the region, you can use either another merge or '
         'a clever groupby.'
     )
-    assert referendum_result_by_region.shape == (13, 6)
+    assert referendum_result_by_regions.shape == (13, 6)
 
     # check that some of the values
-    referendum_result_by_region = referendum_result_by_region.set_index(
+    referendum_result_by_regions = referendum_result_by_regions.set_index(
         'name_reg'
     )
-    assert referendum_result_by_region['Registered'].sum() == 43_262_592
-    assert referendum_result_by_region.loc[
+    assert referendum_result_by_regions['Registered'].sum() == 43_262_592
+    assert referendum_result_by_regions.loc[
         'Normandie', 'Abstentions'] == 426_075
-    assert referendum_result_by_region.loc[
+    assert referendum_result_by_regions.loc[
         'Grand Est', 'Choice A'] == 1_088_684
-    assert referendum_result_by_region.loc['Occitanie', 'Null'] == 62_732
+    assert referendum_result_by_regions.loc['Occitanie', 'Null'] == 62_732
 
 
 def test_plot_referendum_map():
@@ -102,10 +102,10 @@ def test_plot_referendum_map():
     referendum_and_areas = merge_referendum_and_areas(
         referendum, regions_and_departments
     )
-    referendum_result_by_region = compute_referendum_result_by_regions(
+    referendum_result_by_regions = compute_referendum_result_by_regions(
         referendum_and_areas
     )
-    gdf_referendum = plot_referendum_map(referendum_result_by_region)
+    gdf_referendum = plot_referendum_map(referendum_result_by_regions)
 
     assert isinstance(gdf_referendum, gpd.GeoDataFrame), (
         "The return object should be a GeoDataFrame, not a "