Create app.py

app.py

@@ -0,0 +1,94 @@
+# app.py
+
+import streamlit as st
+import pandas as pd
+import numpy as np
+import joblib
+from eda import (average_sales_by_region, average_sales_and_profit_over_time, 
+                 segment_vs_region_distribution, sales_vs_profit_across_segments, 
+                 category_composition_for_profit_and_sales)
+from prediction import make_prediction
+
+# Load the dataset for EDA
+@st.cache
+def load_data():
+    return pd.read_csv('your_dataset.csv')
+
+df = load_data()
+
+# Load the pipeline and model for predictions
+pipeline = joblib.load('full_pipeline_with_unit_price.pkl')
+model = joblib.load('best_model.pkl')
+
+# Sidebar for navigation
+st.sidebar.title("Navigation")
+selection = st.sidebar.radio("Go to", ["Home", "EDA", "Make a Prediction"])
+
+if selection == "Home":
+    st.title("Welcome to the Superstore Sales Dashboard")
+
+elif selection == "EDA":
+    st.title("Exploratory Data Analysis (EDA)")
+    
+    # Average Sales by Region
+    st.header("Average Sales by Region")
+    fig1 = average_sales_by_region(df)
+    st.pyplot(fig1)
+    
+    # Average Sales and Profit Over Time
+    st.header("Average Sales and Profit Over Time")
+    fig2 = average_sales_and_profit_over_time(df)
+    st.pyplot(fig2)
+    
+    # Segment vs. Region Distribution
+    st.header("Segment vs. Region Distribution")
+    fig3 = segment_vs_region_distribution(df)
+    st.pyplot(fig3)
+    
+    # Sales vs. Profit Across Different Customer Segments
+    st.header("Sales vs. Profit Across Different Customer Segments")
+    fig4 = sales_vs_profit_across_segments(df)
+    st.pyplot(fig4)
+    
+    # Category Composition for Profit and Sales
+    st.header("Category Composition for Profit and Sales")
+    fig5 = category_composition_for_profit_and_sales(df)
+    st.pyplot(fig5)
+    
+elif selection == "Make a Prediction":
+    st.title("Make a Sales Prediction")
+            # Input form
+    with st.form("input_form"):
+        row_id = st.number_input('Row ID', min_value=1, value=1, step=1)
+        order_id = st.text_input('Order ID')
+        order_date = st.date_input('Order Date')
+        ship_date = st.date_input('Ship Date')
+        ship_mode = st.selectbox('Ship Mode', ['First Class', 'Second Class', 'Standard Class', 'Same Day'])
+        customer_id = st.text_input('Customer ID')
+        customer_name = st.text_input('Customer Name')
+        segment = st.selectbox('Segment', ['Consumer', 'Corporate', 'Home Office'])
+        country = st.text_input('Country', value='United States')
+        city = st.text_input('City')
+        state = st.text_input('State')
+        postal_code = st.text_input('Postal Code')
+        region = st.selectbox('Region', ['South', 'West', 'Central', 'East'])
+        product_id = st.text_input('Product ID')
+        category = st.selectbox('Category', ['Furniture', 'Office Supplies', 'Technology'])
+        sub_category = st.selectbox('Sub-Category', ['Bookcases', 'Chairs', 'Labels', 'Tables', 'Storage', 'Furnishings', 'Art', 'Phones', 'Binders', 'Appliances', 'Paper', 'Accessories', 'Envelopes', 'Fasteners', 'Supplies', 'Machines', 'Copiers'])
+        product_name = st.text_input('Product Name')
+        sales = st.number_input('Sales', value=0.0, format="%.2f")
+        quantity = st.number_input('Quantity', value=1, format="%d")
+        discount = st.number_input('Discount', value=0.0, format="%.2f")
+        profit = st.number_input('Profit', value=0.0, format="%.2f")
+
+        submit_button = st.form_submit_button("Predict")
+
+    if submit_button:
+        # Construct the input DataFrame. Modify as necessary to fit the model's expected input
+        input_data = pd.DataFrame([[sales, quantity, discount, sub_category]], 
+                                      columns=['sales', 'quantity', 'discount', 'sub_category'])
+            
+        # Call prediction function
+        predicted_profit = make_prediction(input_data)
+            
+        st.write(f'Predicted Profit: {predicted_profit:.2f}')