Upload 2 files

app.py

@@ -0,0 +1,153 @@
+import gradio as gr
+import io
+import pandas as pd
+import matplotlib.pyplot as plt
+from contextlib import redirect_stdout
+from pejmanai_data_analysis.app import (
+    read_csv, data_description, data_preprocessing,
+    data_visualization, data_prediction, data_classification
+)
+
+# Function to capture printed output with error handling
+def capture_output(func, *args, **kwargs):
+    f = io.StringIO()
+    try:
+        with redirect_stdout(f):
+            func(*args, **kwargs)
+        return f.getvalue()
+    except Exception as e:
+        return f"Error occurred: {str(e)}"
+
+# Function to handle regression workflow with error handling
+def regression_workflow(csv_file, x_column, y_column, target_column):
+    try:
+        # Capture data description output
+        data_desc = capture_output(data_description, csv_file.name)
+
+        # Step b) Data Preprocessing
+        df_preprocessed = data_preprocessing(csv_file.name)
+
+        # Step c) Data Visualization
+        if pd.api.types.is_numeric_dtype(df_preprocessed[x_column]) and pd.api.types.is_numeric_dtype(df_preprocessed[y_column]):
+            plt.figure(figsize=(16, 12))
+            data_visualization(csv_file.name, x_column, y_column)
+            visualization_output = plt.gcf()
+        else:
+            plt.figure()
+            plt.text(0.5, 0.5, 'Selected columns are not numeric.', fontsize=12, ha='center')
+            visualization_output = plt.gcf()
+
+        # Capture regression output
+        regression_output = capture_output(data_prediction, csv_file.name, target_column)
+        
+        return data_desc, df_preprocessed, visualization_output, regression_output
+    except Exception as e:
+        return f"Error occurred during regression workflow: {str(e)}", None, None, None
+
+# Function to handle classification workflow with error handling
+def classification_workflow(csv_file, x_column, y_column, target_column):
+    try:
+        # Capture data description output
+        data_desc = capture_output(data_description, csv_file.name)
+
+        # Step b) Data Preprocessing
+        df_preprocessed = data_preprocessing(csv_file.name)
+
+        # Step c) Data Visualization
+        if pd.api.types.is_numeric_dtype(df_preprocessed[x_column]) and pd.api.types.is_numeric_dtype(df_preprocessed[y_column]):
+            plt.figure(figsize=(16, 12))
+            data_visualization(csv_file.name, x_column, y_column)
+            visualization_output = plt.gcf()
+        else:
+            plt.figure()
+            plt.text(0.5, 0.5, 'Selected columns are not numeric.', fontsize=12, ha='center')
+            visualization_output = plt.gcf()
+
+        # Capture classification output
+        classification_output = capture_output(data_classification, csv_file.name, target_column)
+        
+        return data_desc, df_preprocessed, visualization_output, classification_output
+    except Exception as e:
+        return f"Error occurred during classification workflow: {str(e)}", None, None, None
+
+# Main Gradio interface function with error handling
+def gradio_interface(option, csv_file, x_column, y_column, target_column):
+    if option == "Regression Problem":
+        return regression_workflow(csv_file, x_column, y_column, target_column)
+    elif option == "Classification Problem":
+        return classification_workflow(csv_file, x_column, y_column, target_column)
+
+# Reset function to clear outputs
+def reset_all():
+    return "", None, None, ""
+
+# Explanation text
+explanation = """
+### PejmanAI Data Analysis Tool
+
+This app uses the `pejmanai_data_analysis` package, available on [PyPI](https://pypi.org/project/pejmanai-data-analysis/). 
+The GitHub repository for the project is available [here](https://github.com/arad1367/pejmanai_data_analysis_pypi_package).
+
+**About the app:**
+- In the visualization part, you must use two numerical columns. If you select string columns, you will not see any output.
+- The target column is the dependent variable on which you want to make predictions.
+- Due to the nature of the `pejmanai_data_analysis` package, the data description and model output are shown in a captured format (this will be addressed in the next version).
+"""
+
+# Footer HTML
+footer = """
+<div style="text-align: center; margin-top: 20px;">
+    <a href="https://www.linkedin.com/in/pejman-ebrahimi-4a60151a7/" target="_blank">LinkedIn</a> |
+    <a href="https://github.com/arad1367" target="_blank">GitHub</a> |
+    <a href="https://arad1367.pythonanywhere.com/" target="_blank">Live demo of my PhD defense</a>
+    <br>
+    Made with 💖 by Pejman Ebrahimi
+</div>
+"""
+
+# Set up the Gradio interface with UI adjustments
+with gr.Blocks(theme='JohnSmith9982/small_and_pretty') as interface:
+    gr.Markdown(explanation)
+    
+    with gr.Row():
+        problem_type = gr.Radio(["Regression Problem", "Classification Problem"], label="Select Problem Type")
+    with gr.Row():
+        csv_file = gr.File(label="Upload CSV File")
+    with gr.Row():
+        x_column = gr.Textbox(label="Enter X Column for Visualization")
+    with gr.Row():
+        y_column = gr.Textbox(label="Enter Y Column for Visualization")
+    with gr.Row():
+        target_column = gr.Textbox(label="Enter Target Column for Model Training")
+    
+    with gr.Row():
+        submit_button = gr.Button("Run Analysis")
+    
+    with gr.Row():
+        data_desc_output = gr.Textbox(label="Data Description", lines=20, placeholder="Data Description Output")
+    with gr.Row():
+        df_preprocessed_output = gr.Dataframe(label="Data Preprocessing Output")
+    with gr.Row():
+        visualization_output = gr.Plot(label="Data Visualization Output")
+    with gr.Row():
+        model_output = gr.Textbox(label="Model Output", lines=20, placeholder="Model Output")
+    
+    with gr.Row():
+        reset_button = gr.Button("Reset Outputs")
+    
+    reset_button.click(
+        fn=reset_all,
+        inputs=[],
+        outputs=[data_desc_output, df_preprocessed_output, visualization_output, model_output]
+    )
+    
+    submit_button.click(
+        fn=gradio_interface,
+        inputs=[problem_type, csv_file, x_column, y_column, target_column],
+        outputs=[data_desc_output, df_preprocessed_output, visualization_output, model_output]
+    )
+    
+    gr.HTML(footer)
+
+# Launch the Gradio interface
+interface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+contextlib
+pejmanai_data_analysis