Upload folder using huggingface_hub

Dockerfile

@@ -22,7 +22,7 @@ RUN apt-get update && apt-get install -y \
 
     curl \
 
-    software-properties-common \
+    # software-properties-common \
 
     git \
 

app.py

@@ -5,63 +5,87 @@ import pandas as pd
 
 # Load data
 def load_data():
-    df = pd.read_csv("processed_data.csv")  # Replace with your dataset
+    df = pd.read_csv("processed_data.csv")  # replace with your dataset
     return df
 
 # Create Streamlit app
 def app():
     # Title for the app
-    st.title("Retail Sales Data Insights Dashboard-Nov 09")
-
-    # Load data
+    st.title("Pizza Sales Data Analysis Dashboard")
     df = load_data()
 
-    # Key Metrics from the data
-    total_orders = df['Transaction ID'].nunique()
-    total_products_sold = df['Quantity'].sum()
-    total_revenue = df['Total Amount'].sum()
-    most_popular_product_cat = df['Product Category'].value_counts().idxmax()
-    most_frequent_age_cat = df['Age Category'].value_counts().idxmax()
+    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
+    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()
+             
 
-    # Display metrics in the sidebar
+     # Sidebar with key metrics
+    # Write a code snippet to display key metrics in the sidebar of a Streamlit application. 
+    # Show the total number of orders, total revenue (formatted as currency), the most popular
+    # 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
     st.sidebar.header("Key Metrics")
     st.sidebar.metric("Total Orders", total_orders)
-    st.sidebar.metric("Total Products Sold", total_products_sold)
     st.sidebar.metric("Total Revenue", f"${total_revenue:,.2f}")
-    st.sidebar.metric("Most Popular Product Category", most_popular_product_cat)
-    st.sidebar.metric("Most Frequent Age Category", most_frequent_age_cat)
+    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
 
-    
     plots = [
-    {"title": "Total Products Sold by Product and Age Categories", "x": "Product Category", "hue": "Age Category"},
-    {"title": "Monthly Revenue Trends by Product Category", "x": "month", "y": "Total Amount", "hue": "Product Category", "estimator": "sum", "marker": "o"},
-    {"title": "Monthly Revenue Trends by Age Category", "x": "month", "y": "Total Amount", "hue": "Age Category", "estimator": "sum", "marker": "o"},
-    {"title": "Revenue by Product Category", "x": "Product Category", "y": "Total Amount", "estimator": "sum"},
+        {"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
     ]
 
     for plot in plots:
         st.header(plot["title"])
 
         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)
 
-        if "Total Products" 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)
-
-        if "Revenue by Product" in plot["title"]:
-            sns.barplot(data=df, x=plot["x"], y=plot["y"], estimator=plot["estimator"], errorbar=None, 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))
+    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)
-        plt.show()
+    st.pyplot(fig)
     
 
 if __name__ == "__main__":