Update app.py

app.py

@@ -1,202 +1,202 @@
-import gradio as gr
-import joblib
-import numpy as np
-import pandas as pd
-import plotly.graph_objects as go
-
-# -----------------------------
-# Load trained model
-# -----------------------------
-MODEL_PATH = "models/influencer_roi_model.joblib"
-model = joblib.load(MODEL_PATH)
-
-# IMPORTANT: These must match the training feature columns (X.columns)
-# We'll load them from a saved list if you created one.
-# If you didn't save feature names yet, do Step 2.1 below.
-FEATURES_PATH = "models/feature_columns.joblib"
-feature_columns = joblib.load(FEATURES_PATH)
-
-
-# -----------------------------
-# Helper: create input row
-# -----------------------------
-def build_input_row(platform, influencer_category, campaign_type,
-                    engagements, estimated_reach, campaign_duration_days,
-                    assumed_cost_usd):
-    """
-    Converts UI inputs into a single-row DataFrame with exact feature columns.
-    We one-hot encode platform/category/type to match training.
-    """
-
-    # Base numeric features
-    base = {
-        "engagements": engagements,
-        "estimated_reach": estimated_reach,
-        "campaign_duration_days": campaign_duration_days,
-    }
-
-    # Build a raw dataframe with the same pre-encoded columns you had before encoding:
-    raw = pd.DataFrame([{
-        **base,
-        "platform": platform,
-        "influencer_category": influencer_category,
-        "campaign_type": campaign_type
-    }])
-
-    # One-hot encode like training (drop_first=True)
-    encoded = pd.get_dummies(
-        raw,
-        columns=["platform", "influencer_category", "campaign_type"],
-        drop_first=True
-    )
-
-    # Align to training columns (missing columns -> 0, extra -> drop)
-    for col in feature_columns:
-        if col not in encoded.columns:
-            encoded[col] = 0
-    encoded = encoded[feature_columns]
-
-    return encoded
-
-
-# -----------------------------
-# Main prediction function
-# -----------------------------
-def predict_sales_and_roi(platform, influencer_category, campaign_type,
-                          engagements, estimated_reach, campaign_duration_days,
-                          assumed_cost_usd):
-    """
-    Predict product_sales and compute an *estimated ROI* using user-provided cost.
-    ROI = (Predicted Sales - Cost) / Cost
-    """
-
-    # Guard against zero/negative cost
-    if assumed_cost_usd <= 0:
-        return "⚠️ Please enter a campaign cost greater than 0.", None
-
-    X_input = build_input_row(
-        platform, influencer_category, campaign_type,
-        engagements, estimated_reach, campaign_duration_days,
-        assumed_cost_usd
-    )
-
-    # Predict sales
-    pred_sales = float(model.predict(X_input)[0])
-
-    # Compute ROI (as %)
-    roi = (pred_sales - assumed_cost_usd) / assumed_cost_usd
-    roi_percent = roi * 100.0
-
-    # Label ROI quality
-    if roi_percent >= 50:
-        roi_label = "🟢 Strong ROI"
-    elif roi_percent >= 0:
-        roi_label = "🟡 Moderate ROI"
-    else:
-        roi_label = "🔴 Negative ROI"
-
-    # Build Plotly chart: Cost vs Predicted Sales
-    fig = go.Figure()
-    fig.add_bar(name="Campaign Cost", x=["Campaign"], y=[assumed_cost_usd])
-    fig.add_bar(name="Predicted Sales", x=["Campaign"], y=[pred_sales])
-    fig.update_layout(
-        barmode="group",
-        title="Spend vs Predicted Return",
-        xaxis_title="",
-        yaxis_title="USD",
-        height=420
-    )
-
-    # Suggestions (simple, user-friendly)
-    tips = []
-    if engagements < 2000:
-        tips.append("Increase engagement (better content hook, CTA, posting time).")
-    if estimated_reach < 10000:
-        tips.append("Improve reach (cross-post, collab posts, hashtags, boosted content).")
-    if campaign_duration_days < 7:
-        tips.append("Consider longer campaigns (more touchpoints often improves conversions).")
-
-    if not tips:
-        tips_text = "Your inputs look strong. Focus on creative quality + audience match."
-    else:
-        tips_text = " • " + "\n • ".join(tips)
-
-    result_md = f"""
-# 📈 Influencer ROI Prediction
-
-### Predicted Financial Return
-- **Predicted Product Sales:** `${pred_sales:,.2f}`
-- **Campaign Cost:** `${assumed_cost_usd:,.2f}`
-- **Estimated ROI:** **{roi_percent:,.2f}%**  — {roi_label}
-
-### What this means
-This prediction helps brands estimate whether a campaign is likely to be profitable **before spending money**.
-
-### Suggestions to improve ROI
-{tips_text}
-"""
-
-    return result_md, fig
-
-
-# -----------------------------
-# UI (modern dashboard feel)
-# -----------------------------
-with gr.Blocks(title="Influencer ROI Prediction Dashboard") as app:
-    with gr.Tab("Home"):
-        gr.Markdown("""
-# ✨ Influencer ROI Prediction Dashboard
-
-This app predicts **financial return (product sales)** from influencer campaign inputs using **Regression ML**.
-
-### Why it matters
-Marketing teams can use this to:
-- Compare influencer platforms (Instagram vs TikTok vs YouTube)
-- Estimate sales impact before launching a campaign
-- Run **what-if scenarios** (change budget, duration, engagement)
-
-➡️ Go to the **Predict** tab to try it.
-""")
-
-    with gr.Tab("Predict"):
-        gr.Markdown("## 🧠 Predict Sales + Estimated ROI")
-
-        with gr.Row():
-            with gr.Column(scale=2):
-                platform = gr.Dropdown(
-                    choices=["Instagram", "YouTube", "TikTok", "Twitter", "Facebook"],
-                    value="Instagram",
-                    label="Platform"
-                )
-                influencer_category = gr.Dropdown(
-                    choices=["Micro", "Macro", "Mega", "Nano"],
-                    value="Micro",
-                    label="Influencer Category"
-                )
-                campaign_type = gr.Dropdown(
-                    choices=["Product Launch", "Brand Awareness", "Seasonal Promo", "Giveaway", "Affiliate"],
-                    value="Brand Awareness",
-                    label="Campaign Type"
-                )
-
-                engagements = gr.Number(value=5000, label="Engagements (likes/comments/etc.)")
-                estimated_reach = gr.Number(value=50000, label="Estimated Reach")
-                campaign_duration_days = gr.Slider(1, 60, value=14, step=1, label="Campaign Duration (days)")
-                assumed_cost_usd = gr.Number(value=1000, label="Campaign Cost (USD)")
-
-                predict_btn = gr.Button("🚀 Predict ROI", variant="primary")
-
-            with gr.Column(scale=3):
-                output_md = gr.Markdown()
-                output_plot = gr.Plot()
-
-        predict_btn.click(
-            fn=predict_sales_and_roi,
-            inputs=[platform, influencer_category, campaign_type,
-                    engagements, estimated_reach, campaign_duration_days,
-                    assumed_cost_usd],
-            outputs=[output_md, output_plot]
-        )
-
-if __name__ == "__main__":
-    app.launch()
+import gradio as gr
+import joblib
+import numpy as np
+import pandas as pd
+import plotly.graph_objects as go
+
+# -----------------------------
+# Load trained model
+# -----------------------------
+MODEL_PATH = "influencer_roi_model.joblib"
+model = joblib.load(MODEL_PATH)
+
+# IMPORTANT: These must match the training feature columns (X.columns)
+# We'll load them from a saved list if you created one.
+# If you didn't save feature names yet, do Step 2.1 below.
+FEATURES_PATH = "feature_columns.joblib"
+feature_columns = joblib.load(FEATURES_PATH)
+
+
+# -----------------------------
+# Helper: create input row
+# -----------------------------
+def build_input_row(platform, influencer_category, campaign_type,
+                    engagements, estimated_reach, campaign_duration_days,
+                    assumed_cost_usd):
+    """
+    Converts UI inputs into a single-row DataFrame with exact feature columns.
+    We one-hot encode platform/category/type to match training.
+    """
+
+    # Base numeric features
+    base = {
+        "engagements": engagements,
+        "estimated_reach": estimated_reach,
+        "campaign_duration_days": campaign_duration_days,
+    }
+
+    # Build a raw dataframe with the same pre-encoded columns you had before encoding:
+    raw = pd.DataFrame([{
+        **base,
+        "platform": platform,
+        "influencer_category": influencer_category,
+        "campaign_type": campaign_type
+    }])
+
+    # One-hot encode like training (drop_first=True)
+    encoded = pd.get_dummies(
+        raw,
+        columns=["platform", "influencer_category", "campaign_type"],
+        drop_first=True
+    )
+
+    # Align to training columns (missing columns -> 0, extra -> drop)
+    for col in feature_columns:
+        if col not in encoded.columns:
+            encoded[col] = 0
+    encoded = encoded[feature_columns]
+
+    return encoded
+
+
+# -----------------------------
+# Main prediction function
+# -----------------------------
+def predict_sales_and_roi(platform, influencer_category, campaign_type,
+                          engagements, estimated_reach, campaign_duration_days,
+                          assumed_cost_usd):
+    """
+    Predict product_sales and compute an *estimated ROI* using user-provided cost.
+    ROI = (Predicted Sales - Cost) / Cost
+    """
+
+    # Guard against zero/negative cost
+    if assumed_cost_usd <= 0:
+        return "⚠️ Please enter a campaign cost greater than 0.", None
+
+    X_input = build_input_row(
+        platform, influencer_category, campaign_type,
+        engagements, estimated_reach, campaign_duration_days,
+        assumed_cost_usd
+    )
+
+    # Predict sales
+    pred_sales = float(model.predict(X_input)[0])
+
+    # Compute ROI (as %)
+    roi = (pred_sales - assumed_cost_usd) / assumed_cost_usd
+    roi_percent = roi * 100.0
+
+    # Label ROI quality
+    if roi_percent >= 50:
+        roi_label = "���� Strong ROI"
+    elif roi_percent >= 0:
+        roi_label = "🟡 Moderate ROI"
+    else:
+        roi_label = "🔴 Negative ROI"
+
+    # Build Plotly chart: Cost vs Predicted Sales
+    fig = go.Figure()
+    fig.add_bar(name="Campaign Cost", x=["Campaign"], y=[assumed_cost_usd])
+    fig.add_bar(name="Predicted Sales", x=["Campaign"], y=[pred_sales])
+    fig.update_layout(
+        barmode="group",
+        title="Spend vs Predicted Return",
+        xaxis_title="",
+        yaxis_title="USD",
+        height=420
+    )
+
+    # Suggestions (simple, user-friendly)
+    tips = []
+    if engagements < 2000:
+        tips.append("Increase engagement (better content hook, CTA, posting time).")
+    if estimated_reach < 10000:
+        tips.append("Improve reach (cross-post, collab posts, hashtags, boosted content).")
+    if campaign_duration_days < 7:
+        tips.append("Consider longer campaigns (more touchpoints often improves conversions).")
+
+    if not tips:
+        tips_text = "Your inputs look strong. Focus on creative quality + audience match."
+    else:
+        tips_text = " • " + "\n • ".join(tips)
+
+    result_md = f"""
+# 📈 Influencer ROI Prediction
+
+### Predicted Financial Return
+- **Predicted Product Sales:** `${pred_sales:,.2f}`
+- **Campaign Cost:** `${assumed_cost_usd:,.2f}`
+- **Estimated ROI:** **{roi_percent:,.2f}%**  — {roi_label}
+
+### What this means
+This prediction helps brands estimate whether a campaign is likely to be profitable **before spending money**.
+
+### Suggestions to improve ROI
+{tips_text}
+"""
+
+    return result_md, fig
+
+
+# -----------------------------
+# UI (modern dashboard feel)
+# -----------------------------
+with gr.Blocks(title="Influencer ROI Prediction Dashboard") as app:
+    with gr.Tab("Home"):
+        gr.Markdown("""
+# ✨ Influencer ROI Prediction Dashboard
+
+This app predicts **financial return (product sales)** from influencer campaign inputs using **Regression ML**.
+
+### Why it matters
+Marketing teams can use this to:
+- Compare influencer platforms (Instagram vs TikTok vs YouTube)
+- Estimate sales impact before launching a campaign
+- Run **what-if scenarios** (change budget, duration, engagement)
+
+➡️ Go to the **Predict** tab to try it.
+""")
+
+    with gr.Tab("Predict"):
+        gr.Markdown("## 🧠 Predict Sales + Estimated ROI")
+
+        with gr.Row():
+            with gr.Column(scale=2):
+                platform = gr.Dropdown(
+                    choices=["Instagram", "YouTube", "TikTok", "Twitter", "Facebook"],
+                    value="Instagram",
+                    label="Platform"
+                )
+                influencer_category = gr.Dropdown(
+                    choices=["Micro", "Macro", "Mega", "Nano"],
+                    value="Micro",
+                    label="Influencer Category"
+                )
+                campaign_type = gr.Dropdown(
+                    choices=["Product Launch", "Brand Awareness", "Seasonal Promo", "Giveaway", "Affiliate"],
+                    value="Brand Awareness",
+                    label="Campaign Type"
+                )
+
+                engagements = gr.Number(value=5000, label="Engagements (likes/comments/etc.)")
+                estimated_reach = gr.Number(value=50000, label="Estimated Reach")
+                campaign_duration_days = gr.Slider(1, 60, value=14, step=1, label="Campaign Duration (days)")
+                assumed_cost_usd = gr.Number(value=1000, label="Campaign Cost (USD)")
+
+                predict_btn = gr.Button("🚀 Predict ROI", variant="primary")
+
+            with gr.Column(scale=3):
+                output_md = gr.Markdown()
+                output_plot = gr.Plot()
+
+        predict_btn.click(
+            fn=predict_sales_and_roi,
+            inputs=[platform, influencer_category, campaign_type,
+                    engagements, estimated_reach, campaign_duration_days,
+                    assumed_cost_usd],
+            outputs=[output_md, output_plot]
+        )
+
+if __name__ == "__main__":
+    app.launch()