Update app.py

app.py

@@ -7,25 +7,34 @@ import pandas as pd
 import re
 from pathlib import Path
 from PIL import Image
-from datetime import datetime
+
 
 # Setting the page configurations
-st.set_page_config(page_title="Sales Prediction Forecasting", page_icon=":heavy_dollar_sign:", layout="wide", initial_sidebar_state="auto")
+st.set_page_config(page_title= "Sales Prediction Forecasting", page_icon= ":heavy_dollar_sign:", layout= "wide", initial_sidebar_state= "auto")
 
 # Setting the page title
 st.title("Grocery Store Sales Time Series Model Prediction")
 
+
+
+
 # Function to load the dataset
 @st.cache_resource
 def load_data(relative_path):
-   data = pd.read_csv(relative_path, index_col=0)
+   data= pd.read_csv(relative_path, index_col= 0)
+   #merged["date"] = pd.to_datetime(merged["date"])
    return data
 
+    
+
+
 # Loading the base dataframe
 rpath = r"merged_train_data.csv"
 data = load_data(rpath)
 
-# Load the model and encoder and scaler
+
+
+# Load the model and encoder ans scaler
 model = pickle.load(open("model.pkl", "rb"))
 encoder = pickle.load(open("encoder.pkl", "rb"))
 scaler = pickle.load(open("scaler.pkl", "rb"))
@@ -35,6 +44,9 @@ header = st.container()
 dataset = st.container()
 features_and_output = st.container()
 
+
+
+
 # Designing the sidebar
 st.sidebar.header("Brief overview of the Columns")
 st.sidebar.markdown(""" 
@@ -57,18 +69,26 @@ with dataset:
         dataset.write("Further information will preview when take a look at the  sidebar")
     dataset.write("---")
 
+
+
+
 # Icon for the page
 image = Image.open(r"beautiful image.png")
 
 # inputs from the user
-form = st.form(key="information", clear_on_submit=False)
+form = st.form(key="information", clear_on_submit=True)
 
 # Structuring the header section
 with header:
     header.write("This an application to build a model that more accurately predicts the unit sales for thousands of items sold at different Favorita stores")
+
     header.image(image)
+   
     header.write("---")
 
+
+ 
+
 # Structuring the features and output section
 with features_and_output:
     features_and_output.subheader("Inputs")
@@ -80,77 +100,108 @@ with features_and_output:
     with form:
         left_col.markdown("***Combined data on Product and Transaction***")
         date = left_col.date_input("Select a date:")
-        family = left_col.selectbox("Product family:", options=sorted(list(data["family"].unique())))
-        onpromotion = left_col.number_input("Number of products on promotion:", min_value=data["onpromotion"].min(), value=data["onpromotion"].min())
-        city = left_col.selectbox("City:", options=sorted(set(data["city"])))
-
+        family = left_col.selectbox("Product family:", options= sorted(list(data["family"].unique())))
+        onpromotion = left_col.number_input("Number of products on promotion:", min_value= data["onpromotion"].min(), value= data["onpromotion"].min())
+        city = left_col.selectbox("City:", options= sorted(set(data["city"])))
+    
         mid_col.markdown("***Data on Location and type***")
-        store_nbr = mid_col.selectbox("Store number:", options=sorted(set(data["store_nbr"])))
-        type_x = mid_col.radio("type_x:", options=sorted(set(data["type_x"])), horizontal=True)
-        type_y = mid_col.radio("type_y:", options=sorted(set(data["type_y"])), horizontal=True)
-        cluster = mid_col.select_slider("Store cluster:", options=sorted(set(data["cluster"])))
-        state = mid_col.selectbox("State:", options=sorted(set(data["state"])))
-
+        store_nbr = mid_col.selectbox("Store number:", options= sorted(set(data["store_nbr"])))
+        type_x = mid_col.radio("type_x:", options= sorted(set(data["type_x"])), horizontal= True)
+        type_y = mid_col.radio("type_y:", options= sorted(set(data["type_y"])), horizontal= True)
+        cluster = mid_col.select_slider("Store cluster:", options= sorted(set(data["cluster"])))
+        state = mid_col.selectbox("State:", options= sorted(set(data["state"])))       
+    
         right_col.markdown("***Data on Economical Factors***")
-        oil_price = right_col.number_input("Oil price:", min_value=data["oil_price"].min(), value=data["oil_price"].min())
-
-    # No submission point, directly make prediction and show results
-    if form:
-        input_dict = {
-            'store_nbr': store_nbr,
-            'cluster': cluster,
-            'city': city,
-            'state': state,
-            'family': family,
-            'type_x': type_x,
-            'type_y': type_y,
-            'onpromotion': onpromotion,
-            'oil_price': oil_price,
-            'date': date
-        }
-        input_df = pd.DataFrame([input_dict])
+        oil_price = right_col.number_input("Oil price:", min_value= data["oil_price"].min(), value= data["oil_price"].min())
         
-        # Function to extract date features
-        def getDateFeatures(df):
-            df['date'] = pd.to_datetime(df['date'])
-            df['day_of_week'] = df['date'].dt.dayofweek
-            df['day_of_month'] = df['date'].dt.day
-            df['month'] = df['date'].dt.month
-            df['year'] = df['date'].dt.year
-            df['quarter'] = df['date'].dt.quarter
-            df['is_weekend'] = df['day_of_week'].isin([5, 6]).astype(int)
-            df['is_month_start'] = df['date'].dt.is_month_start.astype(int)
-            df['is_month_end'] = df['date'].dt.is_month_end.astype(int)
-            df['is_quarter_start'] = df['date'].dt.is_quarter_start.astype(int)
-            df['is_quarter_end'] = df['date'].dt.is_quarter_end.astype(int)
-            df['is_year_start'] = df['date'].dt.is_year_start.astype(int)
-            df['is_year_end'] = df['date'].dt.is_year_end.astype(int)
-            df['days_since_start'] = (df['date'] - datetime(df['date'].dt.year.min(), 1, 1)).dt.days
-            df['days_until_end'] = (datetime(df['date'].dt.year.max(), 12, 31) - df['date']).dt.days
-            df = df.drop('date', axis=1)
-            return df
-
-        # Define the function to make predictions
-        def predict_sales(input_data, input_df):
-            categoric_columns = ['family', 'city', 'state', 'type_y', 'type_x']
-            columns = list(input_df.columns)
-            numeric_columns = [i for i in columns if i not in categoric_columns]
-            scaled_num = scaler.fit_transform(input_df[numeric_columns])
-            encoded_cat = encoder.transform(input_df[categoric_columns])
-            input_data = pd.concat([scaled_num, encoded_cat], axis=1)
-            input_data = input_data.to_numpy()
-            prediction = model.predict(input_data.flatten().reshape(1, -1))
-            return prediction
-
-        input_df = getDateFeatures(input_df)
-        input_df = input_df.drop(columns=['date'], axis=1)
-
-        if st.button('Predict'):
-            prediction = predict_sales(input_df.values, input_df)
-            st.success('The predicted sales amount is $' + str(round(prediction[0], 2)))
-
-# Defining and structuring the footer
+         # Submission point
+        submitted = form.form_submit_button(label= "Submit button")
+
+        if submitted:
+                 with features_and_output:
+                    input_features = {
+                       "date":[date],
+                       "store_nbr": [store_nbr],
+                       "family": [family],
+                       "onpromotion": [onpromotion],
+                       "city": [city],
+                       "state": [state],
+                       "type_x": [type_x],
+                       "cluster":[cluster],
+                       "oil_price": [oil_price],
+                       "type_y": [type_y],
+                    }
+                                  
+
+
+# Define the function to make predictions
+def predict_sales(input_data, input_df):
+    # defining categories and numeric columns
+    categoric_columns = ['family', 'city', 'state', 'type_y', 'type_x']
+    columns = list(input_df.columns) 
+    numeric_columns = [i for i in columns if i not in categoric_columns]
+    scaled_num = scaler.fit_transform(input_df[numeric_columns])
+    encoded_cat = encoder.transform(input_df[categoric_columns])
+    input_data = pd.concat([scaled_num, encoded_cat], axis=1)
+    # convert input_data to a numpy array before flattening to convert it back to a 2D array
+    input_data = input_data.to_numpy()
+    prediction = model.predict(input_data.flatten().reshape(1, -1))
+    return prediction
+
+ #Convert input parameters to a pandas DataFrame
+input_dict = {
+   'store_nbr': store_nbr,
+   'cluster': cluster,
+   'city': city,
+   'state': state,
+   'family': family,
+   'type_x': type_x,
+   'type_y': type_y,
+   'onpromotion': onpromotion,
+   'oil_price': oil_price,
+   'date' : date
+  }
+input_df = pd.DataFrame([input_dict])
+
+
+@st.cache_resource
+def getDateFeatures(df):
+    df['date'] = pd.to_datetime(df['date'], errors='coerce')
+    df['month'] = df['date'].dt.month
+    df['day_of_month'] = df['date'].dt.day
+    df['day_of_year'] = df['date'].dt.dayofyear
+    df['week_of_year'] = df['date'].dt.isocalendar().week
+    df['week_of_year'] = df['week_of_year'].astype(float)
+    df['day_of_week'] = df['date'].dt.dayofweek
+    df['year'] = df['date'].dt.year
+    df["is_weekend"] = np.where(df['day_of_week'] > 4, 1, 0)
+    df['is_month_start'] = df['date'].dt.is_month_start.astype(int)
+    df['quarter'] = df['date'].dt.quarter
+    df['is_month_end'] = df['date'].dt.is_month_end.astype(int)
+    df['is_quarter_start'] = df['date'].dt.is_quarter_start.astype(int)
+    df['is_quarter_end'] = df['date'].dt.is_quarter_end.astype(int)
+    df['is_year_start'] = df['date'].dt.is_year_start.astype(int)
+    df['is_year_end'] = df['date'].dt.is_year_end.astype(int)
+
+    df["season"] = np.where(df.month.isin([12,1,2]), 0, 1)
+    df["season"] = np.where(df.month.isin([6,7,8]), 2, df["season"])
+    df["season"] = pd.Series(np.where(df.month.isin([9, 10, 11]), 3, df["season"])).astype("int8")
+    df['pay_day'] = np.where((df['day_of_month']==15) | (df['is_month_end']==1), 1, 0)
+    df['earthquake_impact'] = np.where(df['date'].isin(
+        pd.date_range(start='2016-04-16', end='2016-12-31', freq='D')), 1, 0)
+
+    return df
+input_df = getDateFeatures(input_df)
+input_df = input_df.drop(columns= ['date'], axis=1)
+
+# Make prediction and show results
+if st.button('Predict'):
+  prediction = predict_sales(input_df.values, input_df)
+  st.success('The predicted sales amount is $' + str(round(prediction[0],2)))
+  
+  
+  # ----- Defining and structuring the footer
 footer = st.expander("**Subsequent Information**")
 with footer:
     if footer.button("Special Thanks"):
-        footer.markdown("*We want to express our appreciation and gratitude to Emmanuel, Rachel, Mavies, and Richard for their great insights and contributions!*")
+        footer.markdown("*We want to express our appreciation and gratitude to Emmanuel,Racheal, Mavies and Richard for their great insights and contributions!*")