Update app.py

app.py

@@ -1,98 +1,142 @@
 import streamlit as st
-import pandas as pd
-import seaborn as sns
-import plotly.express as px
-import os
 
 # Predefined analysis tasks and visualization types
 PREDEFINED_ANALYSIS = {
     "Basic Statistics": {
         "Description": "Generate basic statistics summary for the dataset.",
-        "Code": "st.write(df.describe())"
+        "Function": "show_basic_statistics",
+        "Code": """
+def show_basic_statistics(df):
+    st.write(df.describe())
+"""
     },
     "Correlation Heatmap": {
         "Description": "Generate a correlation heatmap for numeric columns.",
-        "Code": "st.write(df.corr())\nst.write(sns.heatmap(df.corr(), annot=True, cmap='coolwarm'))"
+        "Function": "show_correlation_heatmap",
+        "Code": """
+def show_correlation_heatmap(df):
+    import seaborn as sns
+    st.write(df.corr())
+    st.write(sns.heatmap(df.corr(), annot=True, cmap='coolwarm'))
+"""
     },
     "Histogram": {
         "Description": "Generate a histogram for a selected numeric column.",
+        "Function": "show_histogram",
         "Code": """
-selected_column = st.selectbox("Select a numeric column for the histogram", df.select_dtypes(include='number').columns)
-st.write(px.histogram(df, x=selected_column))
+def show_histogram(df):
+    import plotly.express as px
+    selected_column = st.selectbox("Select a numeric column for the histogram", df.select_dtypes(include='number').columns)
+    st.write(px.histogram(df, x=selected_column))
 """
     },
     "Box Plot": {
         "Description": "Generate a box plot for a selected numeric column.",
+        "Function": "show_box_plot",
         "Code": """
-selected_column = st.selectbox("Select a numeric column for the box plot", df.select_dtypes(include='number').columns)
-st.write(px.box(df, y=selected_column))
+def show_box_plot(df):
+    import plotly.express as px
+    selected_column = st.selectbox("Select a numeric column for the box plot", df.select_dtypes(include='number').columns)
+    st.write(px.box(df, y=selected_column))
 """
     },
     "Scatter Plot": {
         "Description": "Generate a scatter plot for two selected numeric columns.",
+        "Function": "show_scatter_plot",
         "Code": """
-x_column = st.selectbox("Select X-axis column", df.select_dtypes(include='number').columns)
-y_column = st.selectbox("Select Y-axis column", df.select_dtypes(include='number').columns)
-st.write(px.scatter(df, x=x_column, y=y_column))
+def show_scatter_plot(df):
+    import plotly.express as px
+    x_column = st.selectbox("Select X-axis column", df.select_dtypes(include='number').columns)
+    y_column = st.selectbox("Select Y-axis column", df.select_dtypes(include='number').columns)
+    st.write(px.scatter(df, x=x_column, y=y_column))
 """
     },
     "Line Plot": {
         "Description": "Generate a line plot for a selected numeric column.",
+        "Function": "show_line_plot",
         "Code": """
-selected_column = st.selectbox("Select a numeric column for the line plot", df.select_dtypes(include='number').columns)
-st.write(px.line(df, x=df.index, y=selected_column))
+def show_line_plot(df):
+    import plotly.express as px
+    selected_column = st.selectbox("Select a numeric column for the line plot", df.select_dtypes(include='number').columns)
+    st.write(px.line(df, x=df.index, y=selected_column))
 """
     },
     "Bar Chart": {
         "Description": "Generate a bar chart for a selected categorical column.",
+        "Function": "show_bar_chart",
         "Code": """
-selected_column = st.selectbox("Select a categorical column for the bar chart", df.select_dtypes(include='object').columns)
-st.write(px.bar(df, x=selected_column))
+def show_bar_chart(df):
+    import plotly.express as px
+    selected_column = st.selectbox("Select a categorical column for the bar chart", df.select_dtypes(include='object').columns)
+    st.write(px.bar(df, x=selected_column))
 """
     },
     "Pair Plot": {
         "Description": "Generate a pair plot for pairwise relationships between numeric columns.",
-        "Code": "st.write(sns.pairplot(df))"
+        "Function": "show_pair_plot",
+        "Code": """
+def show_pair_plot(df):
+    import seaborn as sns
+    st.write(sns.pairplot(df))
+"""
     },
     "Distribution Plot": {
         "Description": "Generate a distribution plot for a selected numeric column.",
+        "Function": "show_distribution_plot",
         "Code": """
-selected_column = st.selectbox("Select a numeric column for the distribution plot", df.select_dtypes(include='number').columns)
-st.write(sns.displot(df[selected_column], kde=True))
+def show_distribution_plot(df):
+    import seaborn as sns
+    selected_column = st.selectbox("Select a numeric column for the distribution plot", df.select_dtypes(include='number').columns)
+    st.write(sns.displot(df[selected_column], kde=True))
 """
     },
     "Count Plot": {
         "Description": "Generate a count plot for a selected categorical column.",
+        "Function": "show_count_plot",
         "Code": """
-selected_column = st.selectbox("Select a categorical column for the count plot", df.select_dtypes(include='object').columns)
-st.write(sns.countplot(data=df, x=selected_column))
+def show_count_plot(df):
+    import seaborn as sns
+    selected_column = st.selectbox("Select a categorical column for the count plot", df.select_dtypes(include='object').columns)
+    st.write(sns.countplot(data=df, x=selected_column))
 """
     },
     "Pie Chart": {
         "Description": "Generate a pie chart for a selected categorical column.",
+        "Function": "show_pie_chart",
         "Code": """
-selected_column = st.selectbox("Select a categorical column for the pie chart", df.select_dtypes(include='object').columns)
-st.write(px.pie(df, names=selected_column))
+def show_pie_chart(df):
+    import plotly.express as px
+    selected_column = st.selectbox("Select a categorical column for the pie chart", df.select_dtypes(include='object').columns)
+    st.write(px.pie(df, names=selected_column))
 """
     },
     "Area Plot": {
         "Description": "Generate an area plot for a selected numeric column.",
+        "Function": "show_area_plot",
         "Code": """
-selected_column = st.selectbox("Select a numeric column for the area plot", df.select_dtypes(include='number').columns)
-st.write(px.area(df, x=df.index, y=selected_column))
+def show_area_plot(df):
+    import plotly.express as px
+    selected_column = st.selectbox("Select a numeric column for the area plot", df.select_dtypes(include='number').columns)
+    st.write(px.area(df, x=df.index, y=selected_column))
 """
     },
     "Violin Plot": {
         "Description": "Generate a violin plot for a selected numeric column.",
+        "Function": "show_violin_plot",
         "Code": """
-selected_column = st.selectbox("Select a numeric column for the violin plot", df.select_dtypes(include='number').columns)
-st.write(px.violin(df, y=selected_column))
+def show_violin_plot(df):
+    import plotly.express as px
+    selected_column = st.selectbox("Select a numeric column for the violin plot", df.select_dtypes(include='number').columns)
+    st.write(px.violin(df, y=selected_column))
 """
     },
 }
 
 def generate_streamlit_app_code(app_title, app_subtitle, side_panel_title, analysis_tasks, requirements):
     # Generate Python code for the Streamlit app
+    analysis_functions_code = "\n".join([PREDEFINED_ANALYSIS[task]['Code'] for task in analysis_tasks])
+    analysis_tasks_code = "\n        ".join([f"{PREDEFINED_ANALYSIS[task]['Function']}(df)" for task in analysis_tasks])
+    
     code = f"""
 import streamlit as st
 import pandas as pd
@@ -115,7 +159,9 @@ def main():
 
         df = load_data(uploaded_file)
 
-        {analysis_tasks}
+        {analysis_functions_code}
+        
+        {analysis_tasks_code}
 
 if __name__ == "__main__":
     main()
@@ -138,15 +184,10 @@ def main():
 
     if st.button("Generate and Download"):
         if app_title:
-            # Include selected predefined analysis tasks in the app content
-            analysis_tasks_code = ""
-            for task in selected_tasks:
-                analysis_tasks_code += f"\n# {PREDEFINED_ANALYSIS[task]['Description']}\n{PREDEFINED_ANALYSIS[task]['Code']}\n"
-
             # Write generated code to a .py file
             file_path = f"{app_title.replace(' ', '_').lower()}_app.py"
             with open(file_path, "w") as f:
-                f.write(generate_streamlit_app_code(app_title, app_subtitle, side_panel_title, analysis_tasks_code, requirements))
+                f.write(generate_streamlit_app_code(app_title, app_subtitle, side_panel_title, selected_tasks, requirements))
 
             # Write requirements.txt file
             if requirements: