Upload folder using huggingface_hub

github_metrics/developer_survival_plot.py

@@ -0,0 +1,174 @@
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import seaborn as sns
+from lifelines import KaplanMeierFitter
+from matplotlib.colors import LinearSegmentedColormap
+
+from utils import save_plot
+
+
+def load_and_prepare_data(file_path):
+    """
+    Load CSV data, convert 'month_year' to datetime, and prepare cohort and duration calculations.
+    Filter data to include only entries from 2021 onwards and adjust the cohort calculation based on the first active month.
+    Additionally, eliminate all months with a negative 'Order' so we only get the months after the cohort of the individual.
+    """
+    df = pd.read_csv(file_path)
+    df["month_year"] = pd.to_datetime(df["month_year"], format="%B_%Y")
+    df = df[df["month_year"] >= "2021-09-01"]
+    df["Active"] = df["total_commits"] > 0
+    df.sort_values(by=["developer", "month_year"], inplace=True)
+
+    first_active_month = (
+        df[df["Active"]].groupby("developer")["month_year"].min().reset_index()
+    )
+    first_active_month.rename(columns={"month_year": "FirstActiveMonth"}, inplace=True)
+
+    df = df.merge(first_active_month, on="developer", how="left")
+
+    df["Cohort"] = df["FirstActiveMonth"].dt.to_period("M")
+
+    def calculate_order(row):
+        if pd.isnull(row["Cohort"]):
+            return None
+        return (row["month_year"].to_period("M") - row["Cohort"]).n
+
+    df["Order"] = df.apply(calculate_order, axis=1)
+
+    df = df[df["Order"] >= 0]
+    df["Inactive_Month"] = df.groupby("developer")["Active"].transform(
+        lambda x: x.rolling(window=2, min_periods=2).sum() == 0
+    )
+    df["inactive_for_two_months"] = (
+        df.groupby("developer")["Inactive_Month"].transform("max").astype(int)
+    )
+
+    df["duration"] = df.groupby("developer")["month_year"].transform("nunique")
+    df.to_csv("debug.csv", index=False)
+
+    return df
+
+
+def visualize_developer_retention(df):
+    cohort_counts = (
+        df[~df["Inactive_Month"]]
+        .groupby(["Cohort", "Order"])
+        .developer.nunique()
+        .unstack(0)
+    )
+
+    cohort_sizes = cohort_counts.iloc[0]
+    retention = cohort_counts.divide(cohort_sizes, axis=1)
+
+    colors = [(0, "#FF0000"), (0.15, "#FFA500"), (0.2, "#FFFF00"), (1, "#008000")]
+    cmap = LinearSegmentedColormap.from_list("custom_cmap", colors, N=256)
+    plt.figure(figsize=(12, 8))  # Adjusted figure size for better visibility
+    sns.heatmap(retention.T, annot=False, cmap=cmap)
+    plt.title("Journey Through Code: Tracking Developer Engagement Over Time", pad=20)
+
+    plt.subplots_adjust(bottom=0.3)
+
+    description_text = (
+        "This heatmap visualizes the engagement journey of developers, tracked monthly across cohorts."
+        " Each cohort represents developers who began contributing in the same month."
+        " The color gradient from red to green signifies the evolution of active engagement over time,"
+        " with red indicating lower engagement levels and green denoting higher activity."
+        " Cohorts are plotted on the y-axis, and the actual months since the start of the cohort on the x-axis."
+        " This visualization offers insights into how developer activity trends evolve,"
+        " highlighting periods of increased or decreased engagement and aiding in understanding"
+        " the effectiveness of retention strategies over time."
+        " Parameters:"
+        "(a) A developer is considered inactive if they have at least 2 continuous inactive months."
+        "(b) With one commit in a month, the developer is considered active."
+        "(c) The data is filtered to include only entries from September 2021 onwards."
+    )
+    plt.figtext(0.5, -0.0001, description_text, ha="center", fontsize=9, wrap=True)
+
+    save_plot(plt, "developer_engagement_journey")
+
+
+def survival_curve_analysis_and_plot(df):
+    """
+    Perform analysis on the DataFrame to calculate durations and generate visualizations, with annotations explaining the analysis.
+    Adjust the event definition and perform Log-Rank Test.
+    """
+    summary_df = (
+        df.groupby("developer")
+        .agg({"duration": "first", "inactive_for_two_months": "last"})
+        .reset_index()
+    )
+
+    kmf = KaplanMeierFitter()
+    kmf.fit(
+        durations=summary_df["duration"],
+        event_observed=summary_df["inactive_for_two_months"],
+        label="Developer Survival Probability",
+    )
+
+    plt.figure(figsize=(10, 6))
+    ax = plt.subplot(111)
+    kmf.plot_survival_function(ax=ax)
+
+    plt.title("Developer Survival Curve: Probability of Active Contribution Over Time")
+    plt.grid(True, which="both", linestyle="--", linewidth=0.5)
+    median_survival_time = kmf.median_survival_time_
+    ax.axhline(y=0.5, color="red", linestyle="--")
+    ax.text(
+        median_survival_time,
+        0.48,
+        "Median Survival Time",
+        verticalalignment="center",
+        color="red",
+        fontsize=8,
+    )
+    ax.axvline(x=3, color="green", linestyle="--")
+    ax.text(
+        3,
+        0.95,
+        "Inactive Month + 1",
+        verticalalignment="top",
+        horizontalalignment="center",
+        color="green",
+        fontsize=8,
+    )
+    ax.axvline(x=median_survival_time, color="green", linestyle="--")
+    ax.text(
+        len(df["duration"].unique()),
+        0.9,
+        f"After month {int(median_survival_time)} the probability of developers staying is lower than 50 percent",
+        verticalalignment="top",
+        horizontalalignment="right",
+        color="green",
+        fontsize=8,
+    )
+    ax.set_yticks(np.arange(0, 1.1, 0.1))
+
+    # Setting the x-axis and y-axis labels as per the request
+    plt.xlabel("Months since the developer started committing code")
+    plt.ylabel("Probability of a developer staying in the ecosystem")
+
+    description_text = (
+        "The Kaplan-Meier survival curve shows the probability of developers continuing to contribute over time."
+        "Parameters:"
+        "(a) A developer is consider as inactive if they have at least 2 continuous inactive months."
+        "(b) With one commit in a month, the developer is considered active."
+        "(c) The data is filtered to include only entries from September 2021 onwards."
+        "The Kaplan-Meier estimator is a non-parametric statistic used to estimate the survival function from lifetime data."
+        "It requires to know  the duration each subject was observed for, and whether the event of interest"
+        "(in this case, becoming inactive for two months) was observed."
+        "The 'Median Survival Time' shows when the chance of further contributions drops below 50%. "
+        "This analysis helps in understanding the retention of developers and predicting future contribution patterns."
+    )
+    plt.figtext(0.1, -0.1, description_text, ha="left", fontsize=8, wrap=True)
+
+    save_plot(plt, "developer_survival_curve")
+
+
+if __name__ == "__main__":
+    csv_path = "data/source/all_networks_developer_classification.csv"
+    df = load_and_prepare_data(csv_path)
+
+    visualize_developer_retention(df)
+
+    survival_curve_analysis_and_plot(df)

github_metrics/main.py

@@ -1,112 +1,370 @@
 import gradio as gr
 import pandas as pd
-import matplotlib.pyplot as plt
-from io import StringIO
+import plotly.express as px
+import plotly.graph_objects as go
 from termcolor import colored
+from scipy.stats import mannwhitneyu
+from utils import load_all_developers_dataset
 
-# Load the dataset with debug prints
-def load_dataset():
-    try:
-        print(colored("Loading dataset...", "blue"))
-        df = pd.read_csv("data/source/all_networks_developer_classification.csv")
-        # Ensure the month_year column is in the correct datetime format
-        df['month_year'] = pd.to_datetime(df['month_year'], format='%B_%Y')  # Adjust format if necessary
-        return df
-    except Exception as e:
-        print(colored(f"Error loading dataset: {e}", "red"))
-        raise
-
-# Process input and generate plot and classification with debug prints
-def process_input(input_text, uploaded_file):
+def process_input(input_text, uploaded_file, program_end_date=None, event_name=None):
     try:
         print(colored("Processing input...", "blue"))
-
-        # Check if a file was uploaded
         if uploaded_file is not None:
             print(colored("Reading from uploaded file...", "blue"))
-            # Decode the bytes object to string
             file_content = uploaded_file.decode("utf-8")
-            # Split the content by newlines and strip each handle
-            github_handles = [handle.strip() for handle in file_content.split('\n') if handle.strip()]
+            github_handles = [handle.strip() for handle in file_content.split("\n") if handle.strip()]
         else:
             github_handles = [handle.strip() for handle in input_text.split(",")]
-
         print(colored(f"GitHub handles: {github_handles}", "blue"))
 
-        # Load dataset
-        df = load_dataset()
-
-        # Filter dataset for the provided GitHub handles
+        df = load_all_developers_dataset()
         print(colored("Filtering dataset...", "blue"))
-        filtered_df = df[df['developer'].isin(github_handles)]
-
-        # Generate plot
-        print(colored("Generating plot...", "blue"))
-        fig, ax = plt.subplots()
-        for handle in github_handles:
-            dev_df = filtered_df[filtered_df['developer'] == handle]
-            dev_df = dev_df.sort_values('month_year')
-            ax.plot(dev_df['month_year'], dev_df['total_commits'], label=handle)
-
-        ax.set_xlabel("Month")
-        ax.set_ylabel("Number of Commits")
-        ax.legend()
-        plt.xticks(rotation=45)
-        plt.tight_layout()
-
-        # Generate classification table
+        one_year_ago = pd.Timestamp.now() - pd.DateOffset(years=1)
+        filtered_df = df[(df["developer"].isin(github_handles)) & (df["month_year"] >= one_year_ago)]
+        filtered_df = filtered_df.sort_values(by=["developer", "month_year"])
+        filtered_df.loc[:, "month_year"] = pd.to_datetime(filtered_df["month_year"])
+
+        line_fig = create_line_plot(filtered_df, github_handles, program_end_date)
+        analysis_result = perform_statistical_analysis(filtered_df, github_handles, program_end_date)
+        new_developers_count = count_new_developers(filtered_df, github_handles, program_end_date)
+
+        last_3_months = pd.Timestamp.now() - pd.DateOffset(months=3)
+        recent_activity_user = filtered_df[filtered_df["month_year"] >= last_3_months]
+        all_devs_df = load_all_developers_dataset()
+        all_devs_filtered_df = all_devs_df[(all_devs_df["month_year"] >= last_3_months)]
+        other_devs_recent_activity = all_devs_filtered_df[~all_devs_filtered_df["developer"].isin(github_handles)]
+
+        user_specified_active = recent_activity_user[recent_activity_user["total_commits"] > 0]
+        other_developers_active = other_devs_recent_activity[other_devs_recent_activity["total_commits"] > 0]
+        box_fig = create_box_plot(user_specified_active, other_developers_active)
+
         print(colored("Classifying developers...", "blue"))
-        classification = []
-        for handle in github_handles:
-            dev_df = filtered_df[filtered_df['developer'] == handle]
-            last_3_months = pd.Timestamp.now() - pd.DateOffset(months=3)
-            recent_activity = dev_df[dev_df['month_year'] >= last_3_months]
-            total_recent_commits = recent_activity['total_commits'].sum()
-            
-            if dev_df.empty:
-                status = "Always been inactive"
-            elif recent_activity.empty:
-                status = "Previously active but no longer"
-            elif total_recent_commits < 20:
-                status = "Low-level active"
-            else:
-                status = "Highly involved"
-            
-            classification.append((handle, status))
-        
-        classification_df = pd.DataFrame(classification, columns=["Developer", "Classification"]).sort_values("Classification", ascending=False)
+        classification_df = classify_developers(github_handles, recent_activity_user)
         print(colored("Classification completed.", "blue"))
 
-        # Return plot and classification table
-        return fig, classification_df
+        comparison_result = compare_user_developers_to_others(user_specified_active, other_developers_active, df, program_end_date)
+        growth_rate_result = compare_growth_rate(user_specified_active, other_developers_active, df)
+
+        tldr_summary = generate_tldr_summary(github_handles, classification_df, analysis_result, new_developers_count, comparison_result, growth_rate_result, event_name)
+
+        return line_fig, box_fig, classification_df, analysis_result, new_developers_count, comparison_result, growth_rate_result, tldr_summary
     except Exception as e:
         print(colored(f"Error processing input: {e}", "red"))
-        raise
+        return None, None, None, None, "Error in processing input.", None, None, "Error in processing input."
+
+def create_line_plot(filtered_df, github_handles, program_end_date):
+    all_developers = pd.DataFrame({"developer": github_handles, "month_year": pd.Timestamp.now(), "total_commits": 0})
+    plot_df = pd.concat([filtered_df, all_developers])
+    plot_df = plot_df.groupby(["developer", "month_year"])["total_commits"].sum().reset_index()
+    line_fig = px.line(
+        plot_df,
+        x="month_year",
+        y="total_commits",
+        color="developer",
+        labels={"month_year": "Month", "total_commits": "Number of Commits"},
+        title="Commits per Month",
+    )
+    if program_end_date:
+        program_end_date = pd.to_datetime(program_end_date)
+        line_fig.add_vline(x=program_end_date, line_width=2, line_dash="dash", line_color="red")
+    return line_fig
+
+def create_box_plot(user_specified_active, other_developers_active):
+    box_fig = go.Figure()
+    box_fig.add_trace(go.Box(y=user_specified_active["total_commits"], name="User Specified Developers"))
+    box_fig.add_trace(go.Box(y=other_developers_active["total_commits"], name="Other Developers"))
+    box_fig.update_layout(
+        title="Comparison of Monthly Commits in the Last 3 Months: User Specified vs. Other Developers (Active Only)",
+        yaxis_title="Total Monthly Commits",
+        yaxis=dict(range=[0, 50]),
+    )
+    return box_fig
+
+def classify_developers(github_handles, recent_activity_user):
+    classification = []
+    for handle in github_handles:
+        dev_df = recent_activity_user[recent_activity_user["developer"] == handle]
+        total_recent_commits = dev_df["total_commits"].sum()
+        if dev_df.empty or total_recent_commits == 0:
+            status = "Always been inactive"
+        elif total_recent_commits < 20:
+            status = "Low-level active"
+        else:
+            status = "Highly involved"
+        classification.append((handle, status, total_recent_commits))
+
+    sort_keys = {
+        "Highly involved": 1,
+        "Low-level active": 2,
+        "Previously active but no longer": 3,
+        "Always been inactive": 4,
+    }
+    classification_df = pd.DataFrame(classification, columns=["Developer", "Classification", "Total Recent Commits"])
+    classification_df["Sort Key"] = classification_df["Classification"].map(sort_keys)
+    classification_df.sort_values(by=["Sort Key", "Total Recent Commits"], ascending=[True, False], inplace=True)
+    classification_df.drop(["Sort Key", "Total Recent Commits"], axis=1, inplace=True)
+    return classification_df
+
+def perform_statistical_analysis(filtered_df, github_handles, program_end_date_str):
+    if program_end_date_str is None:
+        return "Program end date not provided. Unable to perform statistical analysis."
+
+    program_end_date = pd.to_datetime(program_end_date_str)
+    before_program = filtered_df[filtered_df["month_year"] < program_end_date]
+    after_program = filtered_df[filtered_df["month_year"] >= program_end_date]
+
+    before_counts = before_program.groupby("developer")["total_commits"].median()
+    after_counts = after_program.groupby("developer")["total_commits"].median()
+
+    all_developers = pd.Series(0, index=github_handles)
+    before_counts = before_counts.reindex(all_developers.index, fill_value=0)
+    after_counts = after_counts.reindex(all_developers.index, fill_value=0)
+
+    if len(before_counts) < 2 or len(after_counts) < 2:
+        return "Not enough data for statistical analysis."
+
+    stat, p_value = mannwhitneyu(after_counts, before_counts)
+    analysis_result = f"Mann-Whitney U test statistic: {stat:.3f}, P-value: {p_value:.3f}\n"
+
+    if p_value < 0.2:
+        if stat > 0:
+            analysis_result += "Difference in commit activity before and after the program is considered significant. " \
+                               "The commit activity is higher after the program."
+        else:
+            analysis_result += "Difference in commit activity before and after the program is considered significant. " \
+                               "The commit activity is lower after the program."
+    else:
+        analysis_result += "No significant difference in commit activity before and after the program."
+
+    return analysis_result
+
+def count_new_developers(filtered_df, github_handles, program_end_date_str):
+    if program_end_date_str is None:
+        return "Program end date not provided. Unable to count new developers."
+
+    program_end_date = pd.to_datetime(program_end_date_str)
+    two_months_after_program = program_end_date + pd.DateOffset(months=2)
+
+    before_program = filtered_df[filtered_df["month_year"] < program_end_date]
+    after_program = filtered_df[(filtered_df["month_year"] >= program_end_date) & (filtered_df["month_year"] <= two_months_after_program)]
+
+    before_developers = before_program["developer"].unique()
+    after_developers = after_program["developer"].unique()
+
+    new_developers = set(after_developers) - set(before_developers)
+    new_developers_str = ", ".join(new_developers)
+
+    return f"Number of new developers committing code within 2 months after the program: {len(new_developers)}\nNew developers: {new_developers_str}"
+
+def compare_user_developers_to_others(user_specified_active, other_developers_active, df, program_end_date_str):
+    if program_end_date_str is None:
+        return "Program end date not provided. Unable to compare user-specified developers to others."
+
+    program_end_date = pd.to_datetime(program_end_date_str)
+
+    user_commits = df[(df["developer"].isin(user_specified_active["developer"])) & (df["month_year"] >= program_end_date)]["total_commits"]
+    other_commits = df[(df["developer"].isin(other_developers_active["developer"])) & (df["month_year"] >= program_end_date)]["total_commits"]
+
+    stat, p_value = mannwhitneyu(user_commits, other_commits)
+    comparison_result = f"Mann-Whitney U test statistic: {stat:.3f}, P-value: {p_value:.3f}\n"
+
+    if p_value < 0.25:
+        if stat > 0:
+            comparison_result += "The user-specified developers have a significantly higher number of commits compared to other developers since the program end date."
+        else:
+            comparison_result += "The user-specified developers have a significantly lower number of commits compared to other developers since the program end date."
+    else:
+        comparison_result += "There is no significant difference in the number of commits between user-specified developers and other developers since the program end date."
+
+    return comparison_result
+
+def compare_growth_rate(user_specified_active, other_developers_active, df):
+    user_growth_rates = []
+    other_growth_rates = []
+
+    for developer in user_specified_active["developer"].unique():
+        user_df = df[df["developer"] == developer]
+        user_df = user_df.sort_values("month_year")
+        user_commits = user_df["total_commits"].tolist()
+        user_growth_rate = calculate_average_growth_rate(user_commits)
+        user_growth_rates.append(user_growth_rate)
+
+    for developer in other_developers_active["developer"].unique():
+        other_df = df[df["developer"] == developer]
+        other_df = other_df.sort_values("month_year")
+        other_commits = other_df["total_commits"].tolist()
+        other_growth_rate = calculate_average_growth_rate(other_commits)
+        other_growth_rates.append(other_growth_rate)
+
+    stat, p_value = mannwhitneyu(user_growth_rates, other_growth_rates)
+    comparison_result = f"Mann-Whitney U test statistic: {stat:.3f}, P-value: {p_value:.3f}\n"
+
+    if p_value < 0.25:
+        if stat > 0:
+            comparison_result += "The user-specified developers have a significantly higher average growth rate of commit activity compared to other developers."
+        else:
+            comparison_result += "The user-specified developers have a significantly lower average growth rate of commit activity compared to other developers."
+    else:
+        comparison_result += "There is no significant difference in the average growth rate of commit activity between user-specified developers and other developers."
+
+    return comparison_result
+
+def calculate_average_growth_rate(commits):
+    growth_rates = []
+    for i in range(1, len(commits)):
+        if commits[i - 1] != 0:
+            growth_rate = (commits[i] - commits[i - 1]) / commits[i - 1]
+            growth_rates.append(growth_rate)
+    if len(growth_rates) > 0:
+        return sum(growth_rates) / len(growth_rates)
+    else:
+        return 0
+
+def generate_tldr_summary(github_handles, classification_df, analysis_result, new_developers_count, comparison_result, growth_rate_result, event_name):
+    summary = f"### 📝 TLDR Summary for {', '.join(github_handles)}\n\n"
+
+    highly_involved_devs = classification_df[classification_df["Classification"] == "Highly involved"]["Developer"].tolist()
+    if highly_involved_devs:
+        summary += f"**🌟 High Performers:** {', '.join(highly_involved_devs)}\n\n"
+
+    if "higher after the program" in analysis_result:
+        summary += "**📈 Commit Activity:** Significantly higher after the program.\n\n"
+    elif "lower after the program" in analysis_result:
+        summary += "**📉 Commit Activity:** Significantly lower after the program.\n\n"
+    else:
+        summary += "**🔄 Commit Activity:** No significant change after the program.\n\n"
+
+    if new_developers_count.startswith("Number of new developers"):
+        summary += f"**🆕 New Developers:** {new_developers_count.split(':')[1].strip()}\n\n"
+
+    if "significantly higher number of commits" in comparison_result:
+        summary += "**🔍 Comparison with Other Developers:** User-specified developers have a significantly higher number of commits.\n\n"
+    elif "significantly lower number of commits" in comparison_result:
+        summary += "**🔍 Comparison with Other Developers:** User-specified developers have a significantly lower number of commits.\n\n"
+    else:
+        summary += "**🔍 Comparison with Other Developers:** No significant difference in the number of commits.\n\n"
+
+    if "significantly higher average growth rate" in growth_rate_result:
+        summary += "**📈 Growth Rate:** User-specified developers have a significantly higher average growth rate.\n\n"
+    elif "significantly lower average growth rate" in growth_rate_result:
+        summary += "**📉 Growth Rate:** User-specified developers have a significantly lower average growth rate.\n\n"
+    else:
+        summary += "**🔄 Growth Rate:** No significant difference in the average growth rate.\n\n"
+
+    if event_name:
+        summary += f"*Note: The analysis is based on the {event_name} event.*\n\n"
+
+    return summary
+
 
-# Gradio interface with descriptions and debug prints
 with gr.Blocks() as app:
-    gr.Markdown("## GitHub Starknet Developer Insights")
-    gr.Markdown("""
-    This tool allows you to analyze the GitHub activity of developers within the Starknet ecosystem. 
-    Enter GitHub handles separated by commas or upload a CSV file with GitHub handles in a single column 
-    to see their monthly commit activity and their current involvement classification.
-    """)
-    
+    gr.Markdown("# 🚀 GitHub Starknet Developer Insights")
+    gr.Markdown(
+        """
+        This tool allows you to analyze the GitHub activity of developers within the Starknet ecosystem.
+        Enter GitHub handles separated by commas or upload a CSV file with GitHub handles in a single column
+        to see their monthly commit activity, involvement classification, and comparisons with other developers.
+        """
+    )
+    with gr.Row():
+        with gr.Column():
+            text_input = gr.Textbox(
+                label="Enter GitHub handles separated by commas",
+                placeholder="e.g., user1,user2,user3",
+            )
+            file_input = gr.File(
+                label="Or upload a CSV file with GitHub handles in a single column",
+                type="binary",
+            )
+            gr.Markdown(
+                """
+                *Note:* When uploading a CSV, ensure it contains a single column of GitHub handles without a header row.
+                """
+            )
+            with gr.Row():
+                program_end_date_input = gr.Textbox(label="Program End Date (YYYY-MM-DD)", placeholder="e.g., 2023-06-30")
+                event_name_input = gr.Textbox(label="Event Name (optional)", placeholder="e.g., Basecamp, Hackathon")
+            gr.Markdown(
+                """
+                💡 *Tip: Specifying a program end date allows you to analyze the impact of events like Basecamp or Hackathons on developer activity. Leave it blank to analyze overall activity.*
+                """
+            )
+            btn = gr.Button("Analyze")
+
+        with gr.Column():
+            tldr_output = gr.Markdown(label="📝 TLDR Summary")
+
     with gr.Row():
-        text_input = gr.Textbox(label="Enter GitHub handles separated by commas", placeholder="e.g., user1,user2,user3")
-        file_input = gr.File(label="Or upload a CSV file with GitHub handles in a single column", type="binary")
-    gr.Markdown("""
-    *Note:* When uploading a CSV, ensure it contains a single column of GitHub handles without a header row.
-    """)
-    btn = gr.Button("Analyze")
-    plot_output = gr.Plot(label="Commits per Month")
-    table_output = gr.Dataframe(label="Developer Classification")
+        with gr.Column():
+            plot_output = gr.Plot(label="📈 Commits per Month")
+        with gr.Column():
+            box_plot_output = gr.Plot(label="📊 Box Plot Comparison (Last 3 Months)")
+
+    with gr.Accordion("📊 Statistical Analysis", open=False):
+        stat_analysis_output = gr.Textbox(label="Statistical Analysis Results")
+        gr.Markdown(
+            """
+            The Mann-Whitney U test is used to compare the commit activity of developers before and after the program.
+            - The test statistic measures the difference in the distribution of commits between the two groups (before and after).
+            - The p-value indicates the probability of observing such a difference by chance, assuming there is no real difference between the groups.
+            - A p-value less than 0.2 suggests that the difference is considered significant.
+            - A positive test statistic indicates that the commit activity is higher after the program, while a negative value indicates lower activity.
+            """
+        )
+
+    with gr.Accordion("🆕 New Developers", open=False):
+        new_developers_output = gr.Textbox(label="Number of New Developers")
+
+    with gr.Accordion("🏆 Developer Classification", open=False):
+        table_output = gr.Dataframe(label="Developer Classification")
+        gr.Markdown(
+            """
+            ### Developer Classification Criteria
+            - **Always been inactive**: No commits have been recorded in the dataset.
+            - **Previously active but no longer**: Had commits earlier but none in the last 3 months.
+            - **Low-level active**: Fewer than 20 commits in the last 3 months.
+            - **Highly involved**: 20 or more commits in the last 3 months.
+            """
+        )
 
-    btn.click(process_input, inputs=[text_input, file_input], outputs=[plot_output, table_output])
+    with gr.Accordion("🔍 Comparison with Other Developers", open=False):
+        comparison_output = gr.Textbox(label="Comparison with Other Developers")
+        gr.Markdown(
+            """
+            The Mann-Whitney U test is used to compare the commit activity of the user-specified developers with the rest of the developers in the database since the program end date.
+            - The test statistic measures the difference in the distribution of commits between the two groups.
+            - The p-value indicates the probability of observing such a difference by chance, assuming there is no real difference between the groups.
+            - A p-value less than 0.25 suggests that the difference is considered significant.
+            - If the test statistic is positive, it means the user-specified developers have a higher number of commits compared to other developers, and vice versa.
+            """
+        )
 
-    print(colored("Gradio app initialized.", "blue"))
+    with gr.Accordion("📈 Growth Rate Comparison", open=False):
+        growth_rate_output = gr.Textbox(label="Growth Rate Comparison")
+        gr.Markdown(
+            """
+            The average growth rate of commit activity is compared between the user-specified developers and other developers.
+            - The growth rate is calculated as the relative change in the number of commits from one month to the next.
+            - The Mann-Whitney U test is used to compare the average growth rates between the two groups.
+            - A p-value less than 0.25 suggests that the difference in average growth rates is statistically significant.
+            - If the test statistic is positive, it means the user-specified developers have a higher average growth rate compared to other developers, and vice versa.
+            """
+        )
+
+    gr.Markdown(
+        """
+        💡 *Disclaimer: This information is only for open-source repos and should be taken with a grain of salt. Commits in certain repos may be more important than others, and there are many private repos from several teams that are not included in this analysis.*
+        """
+    )
+
+    btn.click(
+        process_input,
+        inputs=[text_input, file_input, program_end_date_input, event_name_input],
+        outputs=[plot_output, box_plot_output, table_output, stat_analysis_output, new_developers_output, comparison_output, growth_rate_output, tldr_output],
+    )
+
+print(colored("Gradio app initialized.", "blue"))
 
 if __name__ == "__main__":
     print(colored("Launching app...", "blue"))
-    app.launch(share=True)
-
+    app.launch(share=True)

github_metrics/utils.py

@@ -0,0 +1,24 @@
+from datetime import datetime
+from termcolor import colored
+import pandas as pd
+
+
+def load_all_developers_dataset():
+    try:
+        print(colored("Loading dataset...", "blue"))
+        df = pd.read_csv("data/source/all_networks_developer_classification.csv")
+        df["month_year"] = pd.to_datetime(df["month_year"], format="%B_%Y")
+        return df
+    except Exception as e:
+        print(colored(f"Error loading dataset: {e}", "red"))
+        raise
+
+
+def save_plot(plt, base_filename):
+    """
+    Save a matplotlib plot to a file with a timestamped filename.
+    """
+    current_date = datetime.now().strftime("%Y-%m-%d")
+    filename = f"data/figures/{base_filename}_{current_date}.png"
+    plt.savefig(filename, dpi=300, bbox_inches="tight")
+    plt.close()

poetry.lock

@@ -84,6 +84,35 @@ tests = ["attrs[tests-no-zope]", "zope-interface"]
 tests-mypy = ["mypy (>=1.6)", "pytest-mypy-plugins"]
 tests-no-zope = ["attrs[tests-mypy]", "cloudpickle", "hypothesis", "pympler", "pytest (>=4.3.0)", "pytest-xdist[psutil]"]
 
+[[package]]
+name = "autograd"
+version = "1.6.2"
+description = "Efficiently computes derivatives of numpy code."
+optional = false
+python-versions = "*"
+files = [
+    {file = "autograd-1.6.2-py3-none-any.whl", hash = "sha256:208dde2a938e63b4f8f5049b1985505139e529068b0d26f8cd7771fd3eb145d5"},
+    {file = "autograd-1.6.2.tar.gz", hash = "sha256:8731e08a0c4e389d8695a40072ada4512641c113b6cace8f4cfbe8eb7e9aedeb"},
+]
+
+[package.dependencies]
+future = ">=0.15.2"
+numpy = ">=1.12"
+
+[[package]]
+name = "autograd-gamma"
+version = "0.5.0"
+description = "Autograd compatible approximations to the gamma family of functions"
+optional = false
+python-versions = "*"
+files = [
+    {file = "autograd-gamma-0.5.0.tar.gz", hash = "sha256:f27abb7b8bb9cffc8badcbf59f3fe44a9db39e124ecacf1992b6d952934ac9c4"},
+]
+
+[package.dependencies]
+autograd = ">=1.2.0"
+scipy = ">=1.2.0"
+
 [[package]]
 name = "certifi"
 version = "2024.2.2"
@@ -407,6 +436,29 @@ ufo = ["fs (>=2.2.0,<3)"]
 unicode = ["unicodedata2 (>=15.1.0)"]
 woff = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "zopfli (>=0.1.4)"]
 
+[[package]]
+name = "formulaic"
+version = "1.0.1"
+description = "An implementation of Wilkinson formulas."
+optional = false
+python-versions = ">=3.7.2"
+files = [
+    {file = "formulaic-1.0.1-py3-none-any.whl", hash = "sha256:be9e6127b98ba0293654be528fd070ede264f64d0247477c4d5af799b0b12cf2"},
+    {file = "formulaic-1.0.1.tar.gz", hash = "sha256:64dd7992a7aa5bbceb1e40679d0f01fc6f0ba12b7d23d78094a88c2edc68fba1"},
+]
+
+[package.dependencies]
+interface-meta = ">=1.2.0"
+numpy = ">=1.16.5"
+pandas = ">=1.0"
+scipy = ">=1.6"
+typing-extensions = ">=4.2.0"
+wrapt = ">=1.0"
+
+[package.extras]
+arrow = ["pyarrow (>=1)"]
+calculus = ["sympy (>=1.3,!=1.10)"]
+
 [[package]]
 name = "fsspec"
 version = "2024.2.0"
@@ -442,6 +494,17 @@ smb = ["smbprotocol"]
 ssh = ["paramiko"]
 tqdm = ["tqdm"]
 
+[[package]]
+name = "future"
+version = "1.0.0"
+description = "Clean single-source support for Python 3 and 2"
+optional = false
+python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*"
+files = [
+    {file = "future-1.0.0-py3-none-any.whl", hash = "sha256:929292d34f5872e70396626ef385ec22355a1fae8ad29e1a734c3e43f9fbc216"},
+    {file = "future-1.0.0.tar.gz", hash = "sha256:bd2968309307861edae1458a4f8a4f3598c03be43b97521076aebf5d94c07b05"},
+]
+
 [[package]]
 name = "gradio"
 version = "4.19.2"
@@ -484,6 +547,23 @@ uvicorn = ">=0.14.0"
 [package.extras]
 oauth = ["authlib", "itsdangerous"]
 
+[[package]]
+name = "gradio-calendar"
+version = "0.0.4"
+description = "Gradio component for selecting dates with a calendar 📆"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "gradio_calendar-0.0.4-py3-none-any.whl", hash = "sha256:32f738ea94ed4dea1e4069a117d907fc3e8a2757fb2f4b0ce67a801f434928df"},
+    {file = "gradio_calendar-0.0.4.tar.gz", hash = "sha256:e4ea93cc7f6284bb8e547bb34d891776f1f0bebd320eae80bd644c0cd30694ce"},
+]
+
+[package.dependencies]
+gradio = ">=4.0,<5.0"
+
+[package.extras]
+dev = ["build", "twine"]
+
 [[package]]
 name = "gradio-client"
 version = "0.10.1"
@@ -617,6 +697,17 @@ files = [
 docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (<7.2.5)", "sphinx (>=3.5)", "sphinx-lint"]
 testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-ruff (>=0.2.1)", "zipp (>=3.17)"]
 
+[[package]]
+name = "interface-meta"
+version = "1.3.0"
+description = "`interface_meta` provides a convenient way to expose an extensible API with enforced method signatures and consistent documentation."
+optional = false
+python-versions = ">=3.7,<4.0"
+files = [
+    {file = "interface_meta-1.3.0-py3-none-any.whl", hash = "sha256:de35dc5241431886e709e20a14d6597ed07c9f1e8b4bfcffde2190ca5b700ee8"},
+    {file = "interface_meta-1.3.0.tar.gz", hash = "sha256:8a4493f8bdb73fb9655dcd5115bc897e207319e36c8835f39c516a2d7e9d79a1"},
+]
+
 [[package]]
 name = "jinja2"
 version = "3.1.3"
@@ -782,6 +873,26 @@ files = [
     {file = "kiwisolver-1.4.5.tar.gz", hash = "sha256:e57e563a57fb22a142da34f38acc2fc1a5c864bc29ca1517a88abc963e60d6ec"},
 ]
 
+[[package]]
+name = "lifelines"
+version = "0.28.0"
+description = "Survival analysis in Python, including Kaplan Meier, Nelson Aalen and regression"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "lifelines-0.28.0-py3-none-any.whl", hash = "sha256:eacade0527a62d6086cb76f7dbf1e94f2f445a696dd7168723bc7a86e4737a99"},
+    {file = "lifelines-0.28.0.tar.gz", hash = "sha256:eecf726453fd409c94fef8a521f8e593bcd09337f920fe885131f01cfe58b25e"},
+]
+
+[package.dependencies]
+autograd = ">=1.5"
+autograd-gamma = ">=0.3"
+formulaic = ">=0.2.2"
+matplotlib = ">=3.0"
+numpy = ">=1.14.0,<2.0"
+pandas = ">=1.2.0"
+scipy = ">=1.2.0"
+
 [[package]]
 name = "markdown-it-py"
 version = "3.0.0"
@@ -1206,6 +1317,21 @@ tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "pa
 typing = ["typing-extensions"]
 xmp = ["defusedxml"]
 
+[[package]]
+name = "plotly"
+version = "5.19.0"
+description = "An open-source, interactive data visualization library for Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "plotly-5.19.0-py3-none-any.whl", hash = "sha256:906abcc5f15945765328c5d47edaa884bc99f5985fbc61e8cd4dc361f4ff8f5a"},
+    {file = "plotly-5.19.0.tar.gz", hash = "sha256:5ea91a56571292ade3e3bc9bf712eba0b95a1fb0a941375d978cc79432e055f4"},
+]
+
+[package.dependencies]
+packaging = "*"
+tenacity = ">=6.2.0"
+
 [[package]]
 name = "pydantic"
 version = "2.6.2"
@@ -1642,6 +1768,69 @@ files = [
     {file = "ruff-0.2.2.tar.gz", hash = "sha256:e62ed7f36b3068a30ba39193a14274cd706bc486fad521276458022f7bccb31d"},
 ]
 
+[[package]]
+name = "scipy"
+version = "1.12.0"
+description = "Fundamental algorithms for scientific computing in Python"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "scipy-1.12.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:78e4402e140879387187f7f25d91cc592b3501a2e51dfb320f48dfb73565f10b"},
+    {file = "scipy-1.12.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:f5f00ebaf8de24d14b8449981a2842d404152774c1a1d880c901bf454cb8e2a1"},
+    {file = "scipy-1.12.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e53958531a7c695ff66c2e7bb7b79560ffdc562e2051644c5576c39ff8efb563"},
+    {file = "scipy-1.12.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e32847e08da8d895ce09d108a494d9eb78974cf6de23063f93306a3e419960c"},
+    {file = "scipy-1.12.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4c1020cad92772bf44b8e4cdabc1df5d87376cb219742549ef69fc9fd86282dd"},
+    {file = "scipy-1.12.0-cp310-cp310-win_amd64.whl", hash = "sha256:75ea2a144096b5e39402e2ff53a36fecfd3b960d786b7efd3c180e29c39e53f2"},
+    {file = "scipy-1.12.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:408c68423f9de16cb9e602528be4ce0d6312b05001f3de61fe9ec8b1263cad08"},
+    {file = "scipy-1.12.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:5adfad5dbf0163397beb4aca679187d24aec085343755fcdbdeb32b3679f254c"},
+    {file = "scipy-1.12.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c3003652496f6e7c387b1cf63f4bb720951cfa18907e998ea551e6de51a04467"},
+    {file = "scipy-1.12.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b8066bce124ee5531d12a74b617d9ac0ea59245246410e19bca549656d9a40a"},
+    {file = "scipy-1.12.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:8bee4993817e204d761dba10dbab0774ba5a8612e57e81319ea04d84945375ba"},
+    {file = "scipy-1.12.0-cp311-cp311-win_amd64.whl", hash = "sha256:a24024d45ce9a675c1fb8494e8e5244efea1c7a09c60beb1eeb80373d0fecc70"},
+    {file = "scipy-1.12.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:e7e76cc48638228212c747ada851ef355c2bb5e7f939e10952bc504c11f4e372"},
+    {file = "scipy-1.12.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:f7ce148dffcd64ade37b2df9315541f9adad6efcaa86866ee7dd5db0c8f041c3"},
+    {file = "scipy-1.12.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c39f92041f490422924dfdb782527a4abddf4707616e07b021de33467f917bc"},
+    {file = "scipy-1.12.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a7ebda398f86e56178c2fa94cad15bf457a218a54a35c2a7b4490b9f9cb2676c"},
+    {file = "scipy-1.12.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:95e5c750d55cf518c398a8240571b0e0782c2d5a703250872f36eaf737751338"},
+    {file = "scipy-1.12.0-cp312-cp312-win_amd64.whl", hash = "sha256:e646d8571804a304e1da01040d21577685ce8e2db08ac58e543eaca063453e1c"},
+    {file = "scipy-1.12.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:913d6e7956c3a671de3b05ccb66b11bc293f56bfdef040583a7221d9e22a2e35"},
+    {file = "scipy-1.12.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:bba1b0c7256ad75401c73e4b3cf09d1f176e9bd4248f0d3112170fb2ec4db067"},
+    {file = "scipy-1.12.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:730badef9b827b368f351eacae2e82da414e13cf8bd5051b4bdfd720271a5371"},
+    {file = "scipy-1.12.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6546dc2c11a9df6926afcbdd8a3edec28566e4e785b915e849348c6dd9f3f490"},
+    {file = "scipy-1.12.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:196ebad3a4882081f62a5bf4aeb7326aa34b110e533aab23e4374fcccb0890dc"},
+    {file = "scipy-1.12.0-cp39-cp39-win_amd64.whl", hash = "sha256:b360f1b6b2f742781299514e99ff560d1fe9bd1bff2712894b52abe528d1fd1e"},
+    {file = "scipy-1.12.0.tar.gz", hash = "sha256:4bf5abab8a36d20193c698b0f1fc282c1d083c94723902c447e5d2f1780936a3"},
+]
+
+[package.dependencies]
+numpy = ">=1.22.4,<1.29.0"
+
+[package.extras]
+dev = ["click", "cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy", "pycodestyle", "pydevtool", "rich-click", "ruff", "types-psutil", "typing_extensions"]
+doc = ["jupytext", "matplotlib (>2)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (==0.9.0)", "sphinx (!=4.1.0)", "sphinx-design (>=0.2.0)"]
+test = ["asv", "gmpy2", "hypothesis", "mpmath", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
+
+[[package]]
+name = "seaborn"
+version = "0.13.2"
+description = "Statistical data visualization"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "seaborn-0.13.2-py3-none-any.whl", hash = "sha256:636f8336facf092165e27924f223d3c62ca560b1f2bb5dff7ab7fad265361987"},
+    {file = "seaborn-0.13.2.tar.gz", hash = "sha256:93e60a40988f4d65e9f4885df477e2fdaff6b73a9ded434c1ab356dd57eefff7"},
+]
+
+[package.dependencies]
+matplotlib = ">=3.4,<3.6.1 || >3.6.1"
+numpy = ">=1.20,<1.24.0 || >1.24.0"
+pandas = ">=1.2"
+
+[package.extras]
+dev = ["flake8", "flit", "mypy", "pandas-stubs", "pre-commit", "pytest", "pytest-cov", "pytest-xdist"]
+docs = ["ipykernel", "nbconvert", "numpydoc", "pydata_sphinx_theme (==0.10.0rc2)", "pyyaml", "sphinx (<6.0.0)", "sphinx-copybutton", "sphinx-design", "sphinx-issues"]
+stats = ["scipy (>=1.7)", "statsmodels (>=0.12)"]
+
 [[package]]
 name = "semantic-version"
 version = "2.10.0"
@@ -1707,6 +1896,20 @@ anyio = ">=3.4.0,<5"
 [package.extras]
 full = ["httpx (>=0.22.0)", "itsdangerous", "jinja2", "python-multipart (>=0.0.7)", "pyyaml"]
 
+[[package]]
+name = "tenacity"
+version = "8.2.3"
+description = "Retry code until it succeeds"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tenacity-8.2.3-py3-none-any.whl", hash = "sha256:ce510e327a630c9e1beaf17d42e6ffacc88185044ad85cf74c0a8887c6a0f88c"},
+    {file = "tenacity-8.2.3.tar.gz", hash = "sha256:5398ef0d78e63f40007c1fb4c0bff96e1911394d2fa8d194f77619c05ff6cc8a"},
+]
+
+[package.extras]
+doc = ["reno", "sphinx", "tornado (>=4.5)"]
+
 [[package]]
 name = "termcolor"
 version = "2.4.0"
@@ -1923,7 +2126,86 @@ files = [
     {file = "websockets-11.0.3.tar.gz", hash = "sha256:88fc51d9a26b10fc331be344f1781224a375b78488fc343620184e95a4b27016"},
 ]
 
+[[package]]
+name = "wrapt"
+version = "1.16.0"
+description = "Module for decorators, wrappers and monkey patching."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "wrapt-1.16.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ffa565331890b90056c01db69c0fe634a776f8019c143a5ae265f9c6bc4bd6d4"},
+    {file = "wrapt-1.16.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e4fdb9275308292e880dcbeb12546df7f3e0f96c6b41197e0cf37d2826359020"},
+    {file = "wrapt-1.16.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bb2dee3874a500de01c93d5c71415fcaef1d858370d405824783e7a8ef5db440"},
+    {file = "wrapt-1.16.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2a88e6010048489cda82b1326889ec075a8c856c2e6a256072b28eaee3ccf487"},
+    {file = "wrapt-1.16.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ac83a914ebaf589b69f7d0a1277602ff494e21f4c2f743313414378f8f50a4cf"},
+    {file = "wrapt-1.16.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:73aa7d98215d39b8455f103de64391cb79dfcad601701a3aa0dddacf74911d72"},
+    {file = "wrapt-1.16.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:807cc8543a477ab7422f1120a217054f958a66ef7314f76dd9e77d3f02cdccd0"},
+    {file = "wrapt-1.16.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:bf5703fdeb350e36885f2875d853ce13172ae281c56e509f4e6eca049bdfb136"},
+    {file = "wrapt-1.16.0-cp310-cp310-win32.whl", hash = "sha256:f6b2d0c6703c988d334f297aa5df18c45e97b0af3679bb75059e0e0bd8b1069d"},
+    {file = "wrapt-1.16.0-cp310-cp310-win_amd64.whl", hash = "sha256:decbfa2f618fa8ed81c95ee18a387ff973143c656ef800c9f24fb7e9c16054e2"},
+    {file = "wrapt-1.16.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:1a5db485fe2de4403f13fafdc231b0dbae5eca4359232d2efc79025527375b09"},
+    {file = "wrapt-1.16.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:75ea7d0ee2a15733684badb16de6794894ed9c55aa5e9903260922f0482e687d"},
+    {file = "wrapt-1.16.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a452f9ca3e3267cd4d0fcf2edd0d035b1934ac2bd7e0e57ac91ad6b95c0c6389"},
+    {file = "wrapt-1.16.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:43aa59eadec7890d9958748db829df269f0368521ba6dc68cc172d5d03ed8060"},
+    {file = "wrapt-1.16.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:72554a23c78a8e7aa02abbd699d129eead8b147a23c56e08d08dfc29cfdddca1"},
+    {file = "wrapt-1.16.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:d2efee35b4b0a347e0d99d28e884dfd82797852d62fcd7ebdeee26f3ceb72cf3"},
+    {file = "wrapt-1.16.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:6dcfcffe73710be01d90cae08c3e548d90932d37b39ef83969ae135d36ef3956"},
+    {file = "wrapt-1.16.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:eb6e651000a19c96f452c85132811d25e9264d836951022d6e81df2fff38337d"},
+    {file = "wrapt-1.16.0-cp311-cp311-win32.whl", hash = "sha256:66027d667efe95cc4fa945af59f92c5a02c6f5bb6012bff9e60542c74c75c362"},
+    {file = "wrapt-1.16.0-cp311-cp311-win_amd64.whl", hash = "sha256:aefbc4cb0a54f91af643660a0a150ce2c090d3652cf4052a5397fb2de549cd89"},
+    {file = "wrapt-1.16.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:5eb404d89131ec9b4f748fa5cfb5346802e5ee8836f57d516576e61f304f3b7b"},
+    {file = "wrapt-1.16.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:9090c9e676d5236a6948330e83cb89969f433b1943a558968f659ead07cb3b36"},
+    {file = "wrapt-1.16.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:94265b00870aa407bd0cbcfd536f17ecde43b94fb8d228560a1e9d3041462d73"},
+    {file = "wrapt-1.16.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f2058f813d4f2b5e3a9eb2eb3faf8f1d99b81c3e51aeda4b168406443e8ba809"},
+    {file = "wrapt-1.16.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:98b5e1f498a8ca1858a1cdbffb023bfd954da4e3fa2c0cb5853d40014557248b"},
+    {file = "wrapt-1.16.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:14d7dc606219cdd7405133c713f2c218d4252f2a469003f8c46bb92d5d095d81"},
+    {file = "wrapt-1.16.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:49aac49dc4782cb04f58986e81ea0b4768e4ff197b57324dcbd7699c5dfb40b9"},
+    {file = "wrapt-1.16.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:418abb18146475c310d7a6dc71143d6f7adec5b004ac9ce08dc7a34e2babdc5c"},
+    {file = "wrapt-1.16.0-cp312-cp312-win32.whl", hash = "sha256:685f568fa5e627e93f3b52fda002c7ed2fa1800b50ce51f6ed1d572d8ab3e7fc"},
+    {file = "wrapt-1.16.0-cp312-cp312-win_amd64.whl", hash = "sha256:dcdba5c86e368442528f7060039eda390cc4091bfd1dca41e8046af7c910dda8"},
+    {file = "wrapt-1.16.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:d462f28826f4657968ae51d2181a074dfe03c200d6131690b7d65d55b0f360f8"},
+    {file = "wrapt-1.16.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a33a747400b94b6d6b8a165e4480264a64a78c8a4c734b62136062e9a248dd39"},
+    {file = "wrapt-1.16.0-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b3646eefa23daeba62643a58aac816945cadc0afaf21800a1421eeba5f6cfb9c"},
+    {file = "wrapt-1.16.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ebf019be5c09d400cf7b024aa52b1f3aeebeff51550d007e92c3c1c4afc2a40"},
+    {file = "wrapt-1.16.0-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:0d2691979e93d06a95a26257adb7bfd0c93818e89b1406f5a28f36e0d8c1e1fc"},
+    {file = "wrapt-1.16.0-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:1acd723ee2a8826f3d53910255643e33673e1d11db84ce5880675954183ec47e"},
+    {file = "wrapt-1.16.0-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:bc57efac2da352a51cc4658878a68d2b1b67dbe9d33c36cb826ca449d80a8465"},
+    {file = "wrapt-1.16.0-cp36-cp36m-win32.whl", hash = "sha256:da4813f751142436b075ed7aa012a8778aa43a99f7b36afe9b742d3ed8bdc95e"},
+    {file = "wrapt-1.16.0-cp36-cp36m-win_amd64.whl", hash = "sha256:6f6eac2360f2d543cc875a0e5efd413b6cbd483cb3ad7ebf888884a6e0d2e966"},
+    {file = "wrapt-1.16.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:a0ea261ce52b5952bf669684a251a66df239ec6d441ccb59ec7afa882265d593"},
+    {file = "wrapt-1.16.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7bd2d7ff69a2cac767fbf7a2b206add2e9a210e57947dd7ce03e25d03d2de292"},
+    {file = "wrapt-1.16.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9159485323798c8dc530a224bd3ffcf76659319ccc7bbd52e01e73bd0241a0c5"},
+    {file = "wrapt-1.16.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a86373cf37cd7764f2201b76496aba58a52e76dedfaa698ef9e9688bfd9e41cf"},
+    {file = "wrapt-1.16.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:73870c364c11f03ed072dda68ff7aea6d2a3a5c3fe250d917a429c7432e15228"},
+    {file = "wrapt-1.16.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:b935ae30c6e7400022b50f8d359c03ed233d45b725cfdd299462f41ee5ffba6f"},
+    {file = "wrapt-1.16.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:db98ad84a55eb09b3c32a96c576476777e87c520a34e2519d3e59c44710c002c"},
+    {file = "wrapt-1.16.0-cp37-cp37m-win32.whl", hash = "sha256:9153ed35fc5e4fa3b2fe97bddaa7cbec0ed22412b85bcdaf54aeba92ea37428c"},
+    {file = "wrapt-1.16.0-cp37-cp37m-win_amd64.whl", hash = "sha256:66dfbaa7cfa3eb707bbfcd46dab2bc6207b005cbc9caa2199bcbc81d95071a00"},
+    {file = "wrapt-1.16.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1dd50a2696ff89f57bd8847647a1c363b687d3d796dc30d4dd4a9d1689a706f0"},
+    {file = "wrapt-1.16.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:44a2754372e32ab315734c6c73b24351d06e77ffff6ae27d2ecf14cf3d229202"},
+    {file = "wrapt-1.16.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8e9723528b9f787dc59168369e42ae1c3b0d3fadb2f1a71de14531d321ee05b0"},
+    {file = "wrapt-1.16.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dbed418ba5c3dce92619656802cc5355cb679e58d0d89b50f116e4a9d5a9603e"},
+    {file = "wrapt-1.16.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:941988b89b4fd6b41c3f0bfb20e92bd23746579736b7343283297c4c8cbae68f"},
+    {file = "wrapt-1.16.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6a42cd0cfa8ffc1915aef79cb4284f6383d8a3e9dcca70c445dcfdd639d51267"},
+    {file = "wrapt-1.16.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:1ca9b6085e4f866bd584fb135a041bfc32cab916e69f714a7d1d397f8c4891ca"},
+    {file = "wrapt-1.16.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:d5e49454f19ef621089e204f862388d29e6e8d8b162efce05208913dde5b9ad6"},
+    {file = "wrapt-1.16.0-cp38-cp38-win32.whl", hash = "sha256:c31f72b1b6624c9d863fc095da460802f43a7c6868c5dda140f51da24fd47d7b"},
+    {file = "wrapt-1.16.0-cp38-cp38-win_amd64.whl", hash = "sha256:490b0ee15c1a55be9c1bd8609b8cecd60e325f0575fc98f50058eae366e01f41"},
+    {file = "wrapt-1.16.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9b201ae332c3637a42f02d1045e1d0cccfdc41f1f2f801dafbaa7e9b4797bfc2"},
+    {file = "wrapt-1.16.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:2076fad65c6736184e77d7d4729b63a6d1ae0b70da4868adeec40989858eb3fb"},
+    {file = "wrapt-1.16.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c5cd603b575ebceca7da5a3a251e69561bec509e0b46e4993e1cac402b7247b8"},
+    {file = "wrapt-1.16.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b47cfad9e9bbbed2339081f4e346c93ecd7ab504299403320bf85f7f85c7d46c"},
+    {file = "wrapt-1.16.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8212564d49c50eb4565e502814f694e240c55551a5f1bc841d4fcaabb0a9b8a"},
+    {file = "wrapt-1.16.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:5f15814a33e42b04e3de432e573aa557f9f0f56458745c2074952f564c50e664"},
+    {file = "wrapt-1.16.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:db2e408d983b0e61e238cf579c09ef7020560441906ca990fe8412153e3b291f"},
+    {file = "wrapt-1.16.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:edfad1d29c73f9b863ebe7082ae9321374ccb10879eeabc84ba3b69f2579d537"},
+    {file = "wrapt-1.16.0-cp39-cp39-win32.whl", hash = "sha256:ed867c42c268f876097248e05b6117a65bcd1e63b779e916fe2e33cd6fd0d3c3"},
+    {file = "wrapt-1.16.0-cp39-cp39-win_amd64.whl", hash = "sha256:eb1b046be06b0fce7249f1d025cd359b4b80fc1c3e24ad9eca33e0dcdb2e4a35"},
+    {file = "wrapt-1.16.0-py3-none-any.whl", hash = "sha256:6906c4100a8fcbf2fa735f6059214bb13b97f75b1a61777fcf6432121ef12ef1"},
+    {file = "wrapt-1.16.0.tar.gz", hash = "sha256:5f370f952971e7d17c7d1ead40e49f32345a7f7a5373571ef44d800d06b1899d"},
+]
+
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.11"
-content-hash = "e649010056241eabfabb2182a733f26410fa16347d695963195d6438fbf4f95d"
+content-hash = "93c07a0e554c6697440ab4476e4eaa56b3e41e1d857b3052df1d13e27ba77c4c"

pyproject.toml

@@ -12,6 +12,12 @@ gradio = "^4.19.2"
 pandas = "^2.2.1"
 matplotlib = "^3.8.3"
 termcolor = "^2.4.0"
+seaborn = "^0.13.2"
+numpy = "^1.26.4"
+lifelines = "^0.28.0"
+plotly = "^5.19.0"
+gradio-calendar = "^0.0.4"
+scipy = "^1.12.0"
 
 
 [build-system]