Upload 2 files

app.py

@@ -0,0 +1,137 @@
+import pandas as pd
+import numpy as np
+import gradio as gr
+import plotly.express as px
+import random
+import warnings
+
+warnings.filterwarnings("ignore")
+random.seed(2025)
+np.random.seed(2025)
+
+def process_data(file):
+    df = pd.read_csv(file.name)
+
+    df.columns = df.columns.str.strip().str.lower()
+    df = df.drop_duplicates()
+
+    for col in ["delivery_time_hours", "expected_time_hours"]:
+        df[col] = df[col].astype(str).str.split(".").str[-1]
+        df[col] = pd.to_numeric(df[col], errors="coerce")
+
+    numeric_cols = [
+        "distance_km","package_weight_kg",
+        "delivery_time_hours","expected_time_hours",
+        "delivery_rating","delivery_cost"
+    ]
+
+    for col in numeric_cols:
+        df[col] = pd.to_numeric(df[col], errors="coerce")
+        df[col] = df[col].fillna(df[col].median())
+
+    categorical_cols = [
+        "delivery_partner","package_type","vehicle_type",
+        "delivery_mode","region","weather_condition",
+        "delayed","delivery_status"
+    ]
+
+    for col in categorical_cols:
+        df[col] = df[col].astype(str).fillna(df[col].mode()[0])
+
+    df["expected_time_hours"] = df["distance_km"] / 45
+    df["delivery_time_hours"] = df["expected_time_hours"] * np.random.uniform(0.9, 1.2, len(df))
+
+    df["delay_hours"] = df["delivery_time_hours"] - df["expected_time_hours"]
+
+    df["delay_score"] = df["delay_hours"].apply(
+        lambda x: 5 if x <= 0 else 4 if x <= 2 else 3 if x <= 5 else 2 if x <= 8 else 1
+    )
+
+    df["performance_label"] = df["delay_score"].map({
+        5:"Excellent",4:"Good",3:"Average",2:"Poor",1:"Critical"
+    })
+
+    return df
+
+def kpi_section(df):
+    avg_delay = round(df["delay_hours"].mean(),2)
+    delay_rate = round((df["delay_hours"] > 0).mean()*100,2)
+    score = round(df["delay_score"].mean(),2)
+
+    return f"""### KPI Overview
+
+- Average Delay: {avg_delay} hours  
+- Delay Rate: {delay_rate}%  
+- Performance Score: {score}  
+"""
+
+def quantitative_section(df):
+    fig1 = px.bar(df.groupby("vehicle_type")["delay_hours"].mean().reset_index(),
+                  x="vehicle_type", y="delay_hours", title="Delay by Vehicle Type")
+
+    fig2 = px.bar(df.groupby("weather_condition")["delay_hours"].mean().reset_index(),
+                  x="weather_condition", y="delay_hours", title="Delay by Weather")
+
+    return fig1, fig2
+
+def qualitative_section(df):
+    worst_vehicle = df.groupby("vehicle_type")["delay_hours"].mean().idxmax()
+    worst_weather = df.groupby("weather_condition")["delay_hours"].mean().idxmax()
+
+    return f"""### Qualitative Insights
+
+The analysis shows that **{worst_vehicle}** vehicles are associated with the highest delays.
+
+Additionally, **{worst_weather}** conditions significantly increase delivery variability.
+
+This suggests both internal and external factors drive delays.
+"""
+
+def recommendation_section(df):
+    best_vehicle = df.groupby("vehicle_type")["delay_score"].mean().idxmax()
+    worst_vehicle = df.groupby("vehicle_type")["delay_score"].mean().idxmin()
+
+    return f"""### AI Management Recommendations
+
+- Use more **{best_vehicle}** vehicles  
+- Reduce reliance on **{worst_vehicle}**  
+- Optimize routes under difficult weather conditions  
+- Improve weakest operational segments  
+"""
+
+def run_dashboard(file):
+    df = process_data(file)
+
+    kpi = kpi_section(df)
+    fig1, fig2 = quantitative_section(df)
+    qual = qualitative_section(df)
+    rec = recommendation_section(df)
+
+    return kpi, fig1, fig2, qual, rec
+
+with gr.Blocks() as demo:
+    gr.Markdown("# AI Delivery Performance Dashboard")
+
+    file_input = gr.File(label="Upload CSV")
+    btn = gr.Button("Generate Dashboard")
+
+    with gr.Tab("1. KPI Overview"):
+        kpi_out = gr.Markdown()
+
+    with gr.Tab("2. Quantitative Analysis"):
+        chart1 = gr.Plot()
+        chart2 = gr.Plot()
+
+    with gr.Tab("3. Qualitative Analysis"):
+        qual_out = gr.Markdown()
+
+    with gr.Tab("4. AI Management Recommendations"):
+        rec_out = gr.Markdown()
+
+    btn.click(
+        run_dashboard,
+        inputs=file_input,
+        outputs=[kpi_out, chart1, chart2, qual_out, rec_out]
+    )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+pandas
+numpy
+plotly