Update app.py

app.py

@@ -38,51 +38,26 @@ model = genai.GenerativeModel(
 )
 
 def calculate_kpis(df):
-    """
-    Calculates key performance indicators from a given transaction dataset.
+    """Calculates KPIs relevant to the given dataset."""
 
-    Args:
-        df: Pandas DataFrame containing transaction data.
+    total_interventions = len(df)
+    interventions_by_category = df['Intervention_Category'].value_counts().to_dict()
+    interventions_by_type = df['Intervention'].value_counts().to_dict()
+    male_participants = len(df[df['Gender'] == 'Male'])
+    female_participants = len(df[df['Gender'] == 'Female'])
+    youth_participants = len(df[df['Youth'] == 'Yes'])
+    non_youth_participants = len(df[df['Youth'] == 'No'])
 
-    Returns:
-        A JSON object containing the calculated KPIs.
-    """
 
-    # Calculate Total Revenue
-    total_revenue = df['Price'] * df['Quantity'].sum()
-
-    # Calculate Top Five Products by Revenue
-    if df['Description'].nunique() > 5:
-        top_five_products = df.groupby('Description')['Price'].sum().nlargest(5).index.tolist()
-    else:
-        top_five_product = "there are less than 5 products in this dataset"
-
-    if df['Branch_Name'].nunique() > 1:
-        best_branch = df.groupby('Branch_Name')['Price'].sum().nlargest(1).index.tolist()
-    else:
-        best_branch = "there is only one branch in this dataset"
-        
-    # Calculate Average Order Value (AOV)
-    aov = df.groupby('Receipt No_')['Price'].sum().mean()
-
-    # Calculate Customer Purchase Frequency (Requires more data for accurate calculation)
-    # Assuming 'Member Card No_' is a unique identifier for customers
-    customer_purchase_frequency = df.groupby('Customer_Name')['Receipt No_'].nunique().mean()
-
-    # Calculate Estimated Customer Lifetime Value (CLTV) (Requires more data for accurate calculation)
-    # Assuming a simple CLTV model based on AOV and purchase frequency
-    estimated_cltv = aov * customer_purchase_frequency * 12  # Assuming annual value
-
-    # Create JSON output
     kpis = {
-        "total_revenue": total_revenue,
-        "top_five_products": top_five_products,
-        "average_order_value": aov,
-        "customer_purchase_frequency": customer_purchase_frequency,
-        "estimated_cltv": estimated_cltv,
-        "best_performing_branch": best_branch
+        "total_interventions": total_interventions,
+        "interventions_by_category": interventions_by_category,
+        "interventions_by_type": interventions_by_type,
+        "male_participants": male_participants,
+        "female_participants": female_participants,
+        "youth_participants": youth_participants,
+        "non_youth_participants": non_youth_participants,
     }
-
     return kpis
 
 
@@ -102,22 +77,102 @@ def generateResponse(dataFrame,prompt):
         answer = pandas_agent.chat(prompt)
         return answer
 
-st.write("# Brave Retail Insights")
+st.write("# Intervention Analytics")
 st.markdown('<style>' + open('./style.css').read() + '</style>', unsafe_allow_html=True)
 st.write("##### Engage in insightful conversations with your data through powerful visualizations")
 with st.sidebar:
-    st.title("Brave Retail Insights")
+    st.title("Intervention Analytics")
     st.sidebar.image("IMG_1181.jpeg", use_column_width=True)
-    tabs = on_hover_tabs(tabName=['Chat', 'Reports'], 
-                         iconName=['chat', 'dashboard'], default_choice=0)
+    tabs = on_hover_tabs(tabName=['Dashboard & Reports', 'Chat'], 
+                         iconName=['dashboard', 'chat'], default_choice=0)
         
 
 
-uploaded_file = "bon_marche.csv"
+uploaded_file = "Intervention.csv"
 #uploaded_file = "healthcare_dataset.csv"
-if tabs =='Chat':
+
+
+if tabs == 'Reports':
+    df = pd.read_csv(uploaded_file)
+
+    st.subheader("Reports")
+    st.write("Filter by Company Name, Product, Gender, Youth, Intervention Category or Intervention to generate report")
+
+    # Filtering Interface
+    st.write("Filtering Options")
+    branch_names = df['Company Name'].unique().tolist() # Company Name instead of Branch Name
+    gender_options = df['Gender'].unique().tolist()
+    youth_options = df['Youth'].unique().tolist()
+    intervention_categories = df['Intervention_Category'].unique().tolist()
+    intervention_types = df['Intervention'].unique().tolist()
+
+
+    selected_companies = st.multiselect('Select Company(ies)', branch_names, default=branch_names)
+    selected_genders = st.multiselect('Select Gender(s)', gender_options, default=gender_options)
+    selected_youth = st.multiselect('Select Youth Status(es)', youth_options, default=youth_options)
+    selected_categories = st.multiselect('Select Intervention Category(ies)', intervention_categories, default=intervention_categories)
+    selected_interventions = st.multiselect('Select Intervention(s)', intervention_types, default=intervention_types)
+
+
+    if st.button('Apply Filters and Generate report'):
+        filtered_df = df.copy()
+
+        if selected_companies:
+            filtered_df = filtered_df[filtered_df['Company Name'].isin(selected_companies)]
+        if selected_genders:
+            filtered_df = filtered_df[filtered_df['Gender'].isin(selected_genders)]
+        if selected_youth:
+            filtered_df = filtered_df[filtered_df['Youth'].isin(selected_youth)]
+        if selected_categories:
+            filtered_df = filtered_df[filtered_df['Intervention_Category'].isin(selected_categories)]
+        if selected_interventions:
+            filtered_df = filtered_df[filtered_df['Intervention'].isin(selected_interventions)]
+
+
+        st.write("Filtered DataFrame")
+        with st.expander("Preview"):
+            st.write(filtered_df.head())
+
+        # Dashboard Visualizations (Plotly)
+        st.subheader("Dashboard")
+
+        col1, col2 = st.columns(2)  # Create two columns for better layout
+
+        with col1:
+            fig_gender = px.histogram(filtered_df, x="Gender", title="Gender Distribution")
+            st.plotly_chart(fig_gender)
+
+            fig_youth = px.histogram(filtered_df, x="Youth", title="Youth Participation")
+            st.plotly_chart(fig_youth)
+
+        with col2:
+            fig_category = px.histogram(filtered_df, x="Intervention_Category", title="Intervention Category Distribution")
+            st.plotly_chart(fig_category)
+
+            fig_intervention = px.histogram(filtered_df, x="Intervention", title="Intervention Type Distribution")
+            st.plotly_chart(fig_intervention)
+
+        with st.spinner("Generating Report, Please Wait...."):
+            prompt = f"""
+You are an expert business analyst. Analyze the following data and generate a comprehensive and insightful business report, including appropriate key performance indicators and recommendations.
+
+Data:
+{str(calculate_kpis(filtered_df))}
+{str(get_pandas_profile(filtered_df))}
+"""
+
+            response = model.generate_content(prompt)
+            report = response.text
+            st.markdown(report)
+            st.success("Report Generated!")
+
+    else:
+        st.write("Filtered DataFrame")
+        st.write("Click 'Apply Filters' to see the filtered data.")
+
+elif tabs =='Chat':
     df = pd.read_csv(uploaded_file)
-    st.subheader("Brave Retail Chat")
+    st.subheader("Chat with AI")
     st.write("Get visualizations and analysis from our Gemini powered agent")
         
         # Read the CSV file
@@ -132,59 +187,4 @@ if tabs =='Chat':
     if user_input:
         answer = generateResponse(dataFrame=df,prompt=user_input)
         st.write(answer)
-
-elif tabs == 'Reports':
-    df = pd.read_csv(uploaded_file)
-    
-
-# Streamlit App
-    st.subheader("Reports")
-    st.write("Filter by Branch Name or Product to generate report")
-
-# Display original 
-
-# Filtering Interface
-    st.write("Filtering Options")
-    branch_names = df['Branch_Name'].unique().tolist()
-    #product_names = df['Description'].unique().tolist()
-    selected_branches = st.multiselect('Select Branch(es) Name', branch_names, default=branch_names)
-    #selected_products = st.multiselect('Select product(s) Name', product_names, default=product_names)
-
-# Button to apply filters
-    if st.button('Apply Filters and Generate report'):
-        df = pd.read_csv(uploaded_file)
-        filtered_df = df.copy()
-    
-    # Apply Branch Name Filter
-        if selected_branches:
-            filtered_df = filtered_df[filtered_df['Branch_Name'].isin(selected_branches)]
-    
-    # Apply Description Filter
-    #if selected_products:
-       # filtered_df = filtered_df[filtered_df['Product_Name'].isin(selected_products)]
-    
-    # Display filtered DataFrame
-            st.write("Filtered DataFrame")
-            with st.expander("Preview"):
-                st.write(filtered_df.head())
-            with st.spinner("Generating Report, Please Wait...."):
-                prompt = """
-You are an expert business analyst. Analyze the following data and generate a comprehensive and insightful business report, including appropriate key perfomance indicators and reccomendations.
-
-data:
-"""  +  str(calculate_kpis(filtered_df)) + str(get_pandas_profile(filtered_df))
-
-                response = model.generate_content(prompt)
-                response2 = generateResponse(filtered_df, "pie chart of revenue by branch")
-                response3 = generateResponse(filtered_df, "bar chart of of most popular products")
-                report = response.text
-                st.markdown(report)
-                # Display the generated images
-                st.markdown(response2)
-                st.markdown(response3)
-                st.success("Report Generated!")
-        else:
-            st.write("Filtered DataFrame")
-            st.write("Click 'Apply Filters' to see the filtered data.")
-