fixed

GitScraping.py

@@ -49,22 +49,38 @@ if __name__ == "__main__":
     
     gender_predictor = GenderPredictor(modelpath)
     
-    repo_url = 'https://github.com/Amstf/DDoS-Attacks-Detection-Using-Adversarial-Neural-Network'
+    repo_url = 'https://gitlab.com/zacchiro/debian-firewoes'
     commit_info = CommitInfo(repo_url)
 
 
     # Get and print the DataFrame with first commit dates for each author
     df,first_commit_dates = commit_info.get_first_commit_dates()
     first_commit_dates[['Predicted_Gender', 'Confidence']] = first_commit_dates['Author'].apply(lambda name: pd.Series(gender_predictor.predict_gender(name)))
+    first_commit_dates['Predicted_Gender'] = first_commit_dates['Predicted_Gender'].replace({0: "Male", 1: "Female", 2: "Unknown"})
+    
     merged_df = df.merge(first_commit_dates[["Author","Predicted_Gender","Confidence"]], on=["Author"])
     # Group by Year and Predicted_Gender, then count the occurrences
+    
+    
+    
     gender_counts = merged_df.groupby(['Year', 'Predicted_Gender']).size().reset_index(name='Count')
 
-    counts = first_commit_dates['Predicted_Gender'].value_counts()
-    labels = ["Male", "Female", "Unknown"]
-    colors = ["blue", "pink", "red"]
-    fig = go.Figure(data=[go.Pie(labels=first_commit_dates['Predicted_Gender'].unique(), values=counts, marker=dict(colors=colors))])
-    # Convert the chart to HTML and return it
-    chart_html = fig.to_html(full_html=False)
+    # counts = first_commit_dates['Predicted_Gender'].value_counts()
+    # labels = ["Male", "Female", "Unknown"]
+    # colors = ["blue", "pink", "red"]
+    # fig = go.Figure(data=[go.Pie(labels=first_commit_dates['Predicted_Gender'].unique(), values=counts, marker=dict(colors=colors))])
+    # # Convert the chart to HTML and return it
+    # chart_html = fig.to_html(full_html=False)
+    gender_counts=gender_counts[gender_counts["Predicted_Gender"]!="Unknown"]
+
+    grouped = gender_counts.groupby('Year').agg({'Count': 'sum'})
+    grouped['Male Percentage'] = gender_counts[gender_counts['Predicted_Gender'] == 'Male'].groupby('Year')['Count'].sum() / grouped['Count'] * 100
+    grouped['Female Percentage'] = gender_counts[gender_counts['Predicted_Gender'] == 'Female'].groupby('Year')['Count'].sum() / grouped['Count'] * 100
+    grouped=grouped.fillna(0)
+    merged_gender_counts = grouped.merge(gender_counts, on=["Year"])[['Year', 'Male Percentage', 'Female Percentage',
+       'Predicted_Gender', 'Count_y']].rename(columns={"Count_y":"Count"})
+    
+    male_count=merged_gender_counts[merged_gender_counts["Predicted_Gender"]=="Male"]
 
+    female_count=merged_gender_counts[merged_gender_counts["Predicted_Gender"]=="Female"]
     print(first_commit_dates)

plot.py

@@ -8,7 +8,8 @@ def get_commits_per_gender(gender_counts):
     grouped['Male Percentage'] = gender_counts[gender_counts['Predicted_Gender'] == 'Male'].groupby('Year')['Count'].sum() / grouped['Count'] * 100
     grouped['Female Percentage'] = gender_counts[gender_counts['Predicted_Gender'] == 'Female'].groupby('Year')['Count'].sum() / grouped['Count'] * 100
     grouped=grouped.fillna(0)
-    merged_gender_counts = grouped.merge(gender_counts[["Year","Predicted_Gender"]], on=["Year"])
+    merged_gender_counts = grouped.merge(gender_counts, on=["Year"])[['Year', 'Male Percentage', 'Female Percentage',
+       'Predicted_Gender', 'Count_y']].rename(columns={"Count_y":"Count"})
     
     male_count=merged_gender_counts[merged_gender_counts["Predicted_Gender"]=="Male"]
     female_count=merged_gender_counts[merged_gender_counts["Predicted_Gender"]=="Female"]
@@ -33,5 +34,4 @@ def get_gender_percentage(df):
     counts = df['Predicted_Gender'].value_counts()
     colors = ["blue", "pink", "gray"]
     Gender_Percentage_plot = go.Figure(data=[go.Pie(labels=df['Predicted_Gender'].unique(), values=counts, marker=dict(colors=colors))])
-    return Gender_Percentage_plot
-
+    return Gender_Percentage_plot