Upload folder using huggingface_hub

Dockerfile

@@ -1,21 +1,21 @@
+# Use a minimal base image with Python 3.9 installed  ##v11
 FROM python:3.9-slim
 
+# Set the working directory inside the container to /app
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    software-properties-common \
-    git \
-    && rm -rf /var/lib/apt/lists/*
 
-COPY requirements.txt ./
-COPY src/ ./src/
+# Copy all files from the current directory on the host to the container's /app directory
+COPY . .
 
+# Install Python dependencies listed in requirements.txt
 RUN pip3 install -r requirements.txt
 
-EXPOSE 8501
 
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
 
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# Define the command to run the Streamlit app on port 8501 and make it accessible externally
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
+
+
+
+# NOTE: Disable XSRF protection for easier external access in order to make batch predictions

app.py

@@ -0,0 +1,68 @@
+import streamlit as st
+import seaborn as sns
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Load data
+def load_data():
+    df = pd.read_csv("processed_data.csv")  # replace with your dataset
+    return df
+
+# Create Streamlit app
+def app():
+    # Title for the app
+    st.title("Pizza Sales Data Analysis Dashboard")
+    df = load_data()
+
+    df = pd.DataFrame(df)
+
+    # Calculate key metrics
+    total_orders = df['order_id'].nunique()
+    total_revenue = df['total_price'].sum()
+    most_popular_size = df['pizza_size'].value_counts().idxmax()
+    most_frequent_category = df['pizza_category'].value_counts().idxmax()
+    total_pizzas_sold = df['quantity'].sum()
+    repeat_customers = df.groupby('order_id').size().value_counts().get(2, 0)
+
+    # Sidebar 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 Size", most_popular_size)
+    st.sidebar.metric("Most Popular Category", most_frequent_category)
+    st.sidebar.metric("Total Pizzas Sold", total_pizzas_sold)
+
+    plots = [
+        {"title": "Top Selling Pizzas (by Quantity)", "x": "pizza_name", "y": "quantity", "top": 5},
+        {"title": "Quantity of Pizzas Sold by Category and Time of the Day", "x": "time_of_day", "hue": "pizza_category"},
+        {"title": "Quantity of Pizzas Sold by Size and Time of the Day", "x": "time_of_day", "hue": "pizza_size"},
+        {"title": "Monthly Revenue Trends by Pizza Category", "x": "order_month", "y": "total_price", "hue": "pizza_category", "estimator": "sum", "marker": "o"},
+    ]
+
+    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)
+
+      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()

requirements.txt

@@ -1,3 +1,5 @@
-altair
-pandas
-streamlit
+pandas==1.5.2
+matplotlib==3.6.2
+seaborn==0.12.1
+scipy==1.10.0
+numpy==1.23.5