add commit counts per years

app.py

@@ -3,6 +3,8 @@ from get_gender import GenderPredictor
 from GitScraping import CommitInfo
 import pandas as pd
 import plotly.graph_objects as go
+from plotly.subplots import make_subplots
+
 class GenderPredictorApp:
     def __init__(self, modelpath):
         self.gender_predictor = GenderPredictor(modelpath)
@@ -16,9 +18,10 @@ class GenderPredictorApp:
         interface1_fn = gr.Interface(fn=self.predict_name, inputs=name, outputs=output, title="GitGender: Exploring Global Gender Disparities in Public Code Contributions")
         name = gr.inputs.Textbox(label="Git-url")
         pie_chart_output = gr.Plot()
-        data_output =gr.Dataframe()
+        histo_chart = gr.Plot()
+        data_output =gr.Dataframe(headers=None)
         # name_buttom = gr.Button("Predict")
-        interface2_fn = gr.Interface(self.predict_github_url, inputs=name, outputs=[pie_chart_output, data_output], title="GitGender: Exploring Global Gender Disparities in Public Code Contributions")
+        interface2_fn = gr.Interface(self.predict_github_url, inputs=name, outputs=[pie_chart_output, data_output,histo_chart], title="GitGender: Exploring Global Gender Disparities in Public Code Contributions")
         demo = gr.TabbedInterface([interface1_fn, interface2_fn], ["Test Model", "Exploring Diversity in GitHub Repositories"])
         self.demo = demo
                 
@@ -46,10 +49,34 @@ class GenderPredictorApp:
         counts = first_commit_dates['Predicted_Gender'].value_counts()
         # print(counts)
         colors = ["blue", "pink", "gray"]
-        fig = go.Figure(data=[go.Pie(labels=first_commit_dates['Predicted_Gender'].unique(), values=counts, marker=dict(colors=colors))])
+        Gender_Percentage = go.Figure(data=[go.Pie(labels=first_commit_dates['Predicted_Gender'].unique(), values=counts, marker=dict(colors=colors))])
+        
+        
+        # ******************************
+        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')
 
+        male_count=gender_counts[gender_counts["Predicted_Gender"]=="Male"]
+        female_count=gender_counts[gender_counts["Predicted_Gender"]=="Female"]
+        fig = make_subplots(rows=1, cols=1, shared_xaxes=True)
+        fig.add_trace(
+            go.Bar(x=male_count['Year'], y=male_count['Count'], name='Male'),
+            row=1, col=1
+        )
+        fig.add_trace(
+            go.Bar(x=female_count['Year'], y=female_count['Count'], name='Female'),
+            row=1, col=1
+        )
+        fig.update_layout(
+            height=400,
+            xaxis=dict(title="gender commits per year"),
+            yaxis1=dict(title='Male'),
+            yaxis2=dict(title='Female'),
+            hovermode='x unified'
+        )
         # Convert the chart to HTML and return it
-        return fig,first_commit_dates[["Author","Author_Timezone","Predicted_Gender"]]
+        return Gender_Percentage,first_commit_dates[["Author","Author_Timezone","Predicted_Gender"]],fig
     def launch(self):
         self.demo.launch()