Upload 5 files

README.md

@@ -1,12 +1,12 @@
 ---
-title: Session5
-emoji: 🏃
-colorFrom: red
-colorTo: gray
+title: Book Analytics Dashboard
+emoji: 📊
 sdk: gradio
-sdk_version: 6.9.0
 app_file: app.py
-pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Book Analytics Dashboard
+
+Run full analytics on fixed datasets.
+
+Click "Run Analysis" to generate results.

app.py

@@ -0,0 +1,74 @@
+# AI-Assisted Code — Academic Integrity Notice
+# Generated with The App Builder. ESCP coursework.
+# Student must be able to explain all code when asked.
+
+import gradio as gr
+import pandas as pd
+import matplotlib.pyplot as plt
+from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
+from statsmodels.tsa.arima.model import ARIMA
+
+def load_data():
+    reviews = pd.read_csv("synthetic_book_reviews.csv")
+    sales = pd.read_csv("synthetic_sales_data.csv")
+    return reviews, sales
+
+def run_sentiment_analysis(df):
+    analyzer = SentimentIntensityAnalyzer()
+    def get_sentiment(text):
+        score = analyzer.polarity_scores(str(text))["compound"]
+        if score >= 0.05:
+            return "Positive"
+        elif score <= -0.05:
+            return "Negative"
+        return "Neutral"
+    df["sentiment"] = df["review"].apply(get_sentiment)
+    return df
+
+def create_sentiment_plot(df):
+    fig, ax = plt.subplots()
+    df["sentiment"].value_counts().plot(kind="bar", ax=ax)
+    ax.set_title("Sentiment Distribution")
+    filepath = "sentiment_plot.png"
+    fig.savefig(filepath)
+    plt.close(fig)
+    return filepath
+
+def forecast_sales(df):
+    df["date"] = pd.to_datetime(df["date"])
+    df = df.sort_values("date")
+    model = ARIMA(df["sales"], order=(1, 1, 1))
+    model_fit = model.fit()
+    return model_fit.forecast(steps=5)
+
+def pricing_decision(sentiment_df, forecast):
+    sentiment_score = sentiment_df["sentiment"].value_counts(normalize=True)
+    positive_ratio = sentiment_score.get("Positive", 0)
+    avg_forecast = forecast.mean()
+    decision = "Increase Price" if positive_ratio > 0.6 else "Keep Price"
+    result = pd.DataFrame({
+        "Positive Sentiment Ratio": [positive_ratio],
+        "Avg Forecast Sales": [avg_forecast],
+        "Decision": [decision]
+    })
+    result.to_csv("pricing_decision.csv", index=False)
+    return result
+
+def run_full_analysis():
+    reviews, sales = load_data()
+    reviews = run_sentiment_analysis(reviews)
+    plot_path = create_sentiment_plot(reviews)
+    forecast = forecast_sales(sales)
+    decision_df = pricing_decision(reviews, forecast)
+    return plot_path, decision_df, "pricing_decision.csv"
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 📊 Automated Book Analytics Dashboard")
+    run_button = gr.Button("Run Analysis")
+    plot_output = gr.Image()
+    table_output = gr.Dataframe()
+    file_output = gr.File()
+    run_button.click(fn=run_full_analysis, inputs=[], outputs=[plot_output, table_output, file_output])
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio==4.36.1
+pandas==2.2.2
+matplotlib==3.8.4
+vaderSentiment==3.3.2
+statsmodels==0.14.2