Upload folder using huggingface_hub

app.py

@@ -4,29 +4,36 @@ import matplotlib.pyplot as plt
 import pandas as pd
 
 # Load data
+@st.cache_data # Cache the data loading to speed up app performance
 def load_data():
+    # Load pre-processed data from csv file
     df = pd.read_csv("processed_data.csv")  # replace with your dataset
+
+    # Ensure order_time is treated as datetime for plots (important since it loses dtype during CSV save/load)
+    if 'order_time' in df.columns:
+        df['order_time'] = pd.to_datetime(df['order_time'])
+    
     return df
 
 # Code to create Streamlit app
 def app():
     # Title for the app
     st.title("Pizza Sales Data Analysis Dashboard")
+    
+    # Load and cache the data
     df = load_data()
 
-    df = pd.DataFrame(df)  # what is this line of code doing?
 
     # Calculate key metrics
     # Write a code snippet to calculate key metrics from the pizza orders dataframe, including the 
     # total number of unique orders, total revenue generated, the most popular pizza size, the most 
     # frequent pizza category, total pizzas sold
 
-    # Code to pull key metrics from dataset
+    # Calculate key metrics from dataset
     total_orders = df['order_id'].nunique()
     total_revenue = df['total_price'].sum()
     most_popular_pizza_size = df['pizza_size'].value_counts().idxmax()
     most_frequent_pizza_category = df['pizza_category'].value_counts().idxmax()
-    most_popular_pizza_name = df['pizza_name'].value_counts().idxmax()
     total_pizzas_sold = df['quantity'].sum()
              
 
@@ -36,57 +43,59 @@ def app():
     # pizza size, the most popular pizza category, and the total number of pizzas sold 
     # using the st.sidebar.metric function.
 
-    # Code to display metrics in sidebar of the report
+    # Generate Sidebar on dashboard with key metrics 
     st.sidebar.header("Key Metrics")
     st.sidebar.metric("Total Orders", total_orders)
     st.sidebar.metric("Total Revenue", f"${total_revenue:,.2f}")
     st.sidebar.metric("Most Popular Pizza Size", most_popular_pizza_size )
     st.sidebar.metric("Most Popular Pizza Category", most_frequent_pizza_category)
-    st.sidebar.metric("Most Popilar Pizza Name", most_popular_pizza_name)
     st.sidebar.metric("Total Pizzas Sold", total_pizzas_sold)
 
-    #"""""""""""""
-
-    # Provide the details of the plots here   **** need to review and update these
-    #plots = [
-    #   {"title": "Top Selling Pizzas (Quantity)", "x": "_________", "y": "___________"},
-    #]
-#  ---------- **** this needs to be reviewed from low code
-
-# Provide the details of the plots here
-# """"""""""""" this is from low code notebook
+  
+    # Plot Configurations for the Reports Dashboard
 
     plots = [
-        {"title": "Top Selling Pizzas (by Quantity)", "x": "pizza_name", "y": "quantity", "top": 5},    #Write the appropriiate column as per the title given
-        {"title": "Quantity of Pizzas Sold by Category and Time of the Day", "x": "pizza_category", "hue": "time_of_day"},   #Write the appropriiate column as per the title given
-        {"title": "Quantity of Pizzas Sold by Size and Time of the Day", "x": "quantity", "hue": "time_of_day"},  #Write the appropriiate column as per the title given
-        {"title": "Monthly Revenue Trends by Pizza Category", "x": "order_month", "y": "total_price", "hue": "pizza_category", "estimator": "sum", "marker": "o"}, #Write the appropriiate column as per the title given
+        {"title": "Top Selling Pizzas (by Quantity)", "type": "bar_sorted", "x": "pizza_name", "y": "quantity", "top": 5},    
+        {"title": "Quantity of Pizzas Sold by Category and Time of the Day", "type": "count", "x": "pizza_category", "hue": "time_of_day"},   
+        {"title": "Quantity of Pizzas Sold by Size and Time of the Day", "type": "count", "x": "pizza_size", "hue": "time_of_day"},  
+        {"title": "Monthly Revenue Trends by Pizza Category", "type": "line", "x": "order_month", "y": "total_price", "hue": "pizza_category", "estimator": "sum", "marker": "o"}, 
     ]
 
+    # Iterate through the plots dictionary above to display them
     for plot in plots:
         st.header(plot["title"])
+        fig, ax = plt.subplots(figsize=(10, 6))
+        
+        if plot["type"] == "bar_sorted":
+            # Bar Plot: Top Selling Pizzas (Custom sorting)
+            plot_var = df.groupby(plot["x"])[plot["y"]].sum().reset_index().sort_values(by=plot["y"], ascending=False).head(plot["top"])
+            sns.barplot(data=plot_var, x=plot["x"], y=plot["y"], ax=ax, palette="plasma")
+            ax.set_xticklabels(ax.get_xticklabels(), rotation=45, ha='right')
+            plt.tight_layout()
+            
+        elif plot["type"] == "count":
+            # Count Plot: Category or Size breakdown
+            sns.countplot(data=df, x=plot["x"], hue=plot["hue"], ax=ax)
+            ax.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.) # Move legend outside
+            
+        elif plot["type"] == "line":
+            # Line Plot: Monthly Revenue Trends
+            # Ensure order_month is treated as categorical for the plot if plotting trends is needed.
+            sns.lineplot(data=df, x=plot["x"], y=plot["y"], hue=plot["hue"], estimator=plot["estimator"], errorbar=None, marker=plot["marker"], ax=ax)
+            ax.set_xticks(df[plot["x"]].unique()) # Ensure ticks are on actual month values
+            
+        
+        # Axis and Final Display Cleanup
+        ax.set_xlabel(" ".join(plot["x"].split("_")).title())
+        
+        if "y" in plot.keys() and plot["y"] != "quantity":
+            ax.set_ylabel(" ".join(plot["y"].split("_")).title())
+        elif plot["type"] != "count":
+             ax.set_ylabel("Quantity")
+        
+        st.pyplot(fig)
+        plt.close(fig) # Close the figure to free up memory
 
-        fig, ax = plt.subplots()
-      
-    if "Top Selling Pizzas" in plot["title"]:
-        data_aux = df.groupby(plot["x"])[plot["y"]].sum().reset_index().sort_values(by=plot["y"], ascending=False).head(plot["top"])
-        ax.bar(data_aux[plot["x"]].values.tolist(), data_aux[plot["y"]].values.tolist())
-      
-    if "Quantity of Pizzas" in plot["title"]:
-        sns.countplot(data=df, x=plot["x"], hue=plot["hue"], ax=ax)
-      
-    if "Monthly Revenue" in plot["title"]:
-        sns.lineplot(data=df, x=plot["x"], y=plot["y"], hue=plot["hue"], estimator=plot["estimator"], errorbar=None, marker=plot["marker"], ax=ax)
-
-    ax.set_xlabel(" ".join(plot["x"].split("_")).capitalize())
-    if "y" in plot.keys():
-        ax.set_ylabel(" ".join(plot["y"].split("_")).capitalize())
-    else:
-        ax.set_ylabel("Quantity")
-        ax.legend(bbox_to_anchor=(1,1))
-
-    st.pyplot(fig)
-    
 
 if __name__ == "__main__":
     app()