app.py

app.py

@@ -0,0 +1,141 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.compose import ColumnTransformer
+from sklearn.pipeline import Pipeline
+from sklearn.multioutput import MultiOutputClassifier
+from sklearn.metrics import accuracy_score
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.linear_model import LogisticRegression
+from sklearn.svm import SVC
+
+# ------------------- Load Data -------------------
+df = pd.read_csv("Balanced_Placement_Data.csv")
+
+features = [
+    'ssc_percentage', 'hsc_percentage', 'undergrad_degree', 'Graduate_degree_percentage',
+    'emp_test_percentage', 'Internship_Experience_Months', 'Certifications_Count',
+    'Technical_Skills_Score', 'Soft_Skills_Score', 'Hackathons_Participated',
+    'Resume_Score', 'Online_Course_Count', 'Social_Media_Presence'
+]
+target_columns = ['Placement_Status', 'Domain_of_Interest']
+
+X = df[features]
+y = df[target_columns]
+
+categorical_features = ['undergrad_degree']
+numerical_features = list(set(features) - set(categorical_features))
+
+preprocessor = ColumnTransformer([
+    ("num", StandardScaler(), numerical_features),
+    ("cat", OneHotEncoder(drop="first"), categorical_features)
+])
+
+models = {
+    "Random Forest": RandomForestClassifier(random_state=42),
+    "Decision Tree": DecisionTreeClassifier(random_state=42),
+    "KNN": KNeighborsClassifier(),
+    "Logistic Regression": LogisticRegression(max_iter=1000),
+    "SVM": SVC(probability=True)
+}
+
+# ------------------- Train Models -------------------
+def train_models():
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size=0.2, random_state=42
+    )
+    results = {}
+    for name, clf in models.items():
+        pipe = Pipeline([
+            ("preprocessor", preprocessor),
+            ("classifier", MultiOutputClassifier(clf))
+        ])
+        pipe.fit(X_train, y_train)
+        y_pred = pipe.predict(X_test)
+
+        placement_acc = accuracy_score(y_test["Placement_Status"], y_pred[:,0])
+        domain_acc = accuracy_score(y_test["Domain_of_Interest"], y_pred[:,1])
+
+        results[name] = {
+            "Placement Accuracy": placement_acc,
+            "Domain Accuracy": domain_acc,
+            "Model": pipe
+        }
+    return results
+
+results = train_models()
+best_model_name = max(results, key=lambda m: results[m]["Placement Accuracy"] + results[m]["Domain Accuracy"])
+best_model = results[best_model_name]["Model"]
+
+# ------------------- Prediction Function -------------------
+def predict_placement_and_domain(
+    ssc_percentage, hsc_percentage, undergrad_degree, Graduate_degree_percentage,
+    emp_test_percentage, Internship_Experience_Months, Certifications_Count,
+    Technical_Skills_Score, Soft_Skills_Score, Hackathons_Participated,
+    Resume_Score, Online_Course_Count, Social_Media_Presence
+):
+    user_input = {
+        "ssc_percentage": ssc_percentage,
+        "hsc_percentage": hsc_percentage,
+        "undergrad_degree": undergrad_degree,
+        "Graduate_degree_percentage": Graduate_degree_percentage,
+        "emp_test_percentage": emp_test_percentage,
+        "Internship_Experience_Months": Internship_Experience_Months,
+        "Certifications_Count": Certifications_Count,
+        "Technical_Skills_Score": Technical_Skills_Score,
+        "Soft_Skills_Score": Soft_Skills_Score,
+        "Hackathons_Participated": Hackathons_Participated,
+        "Resume_Score": Resume_Score,
+        "Online_Course_Count": Online_Course_Count,
+        "Social_Media_Presence": Social_Media_Presence
+    }
+
+    input_df = pd.DataFrame([user_input])
+    prediction = best_model.predict(input_df)
+
+    return {
+        "Placement Status": prediction[0][0],
+        "Domain of Interest": prediction[0][1],
+        "Best Model": best_model_name
+    }
+
+# ------------------- Gradio UI -------------------
+with gr.Blocks() as demo:
+    gr.Markdown("# 🎯 Placement & Domain Predictor")
+
+    with gr.Row():
+        with gr.Column():
+            ssc_percentage = gr.Number(label="SSC Percentage", value=70)
+            hsc_percentage = gr.Number(label="HSC Percentage", value=65)
+            undergrad_degree = gr.Dropdown(choices=list(df['undergrad_degree'].unique()), label="Undergrad Degree")
+            Graduate_degree_percentage = gr.Number(label="Graduate Degree %", value=60)
+            emp_test_percentage = gr.Number(label="Employment Test %", value=50)
+            Internship_Experience_Months = gr.Number(label="Internship Months", value=0)
+            Certifications_Count = gr.Number(label="Certifications Count", value=1)
+            Technical_Skills_Score = gr.Number(label="Technical Skills Score", value=60)
+            Soft_Skills_Score = gr.Number(label="Soft Skills Score", value=60)
+            Hackathons_Participated = gr.Number(label="Hackathons Participated", value=1)
+            Resume_Score = gr.Number(label="Resume Score", value=50)
+            Online_Course_Count = gr.Number(label="Online Course Count", value=2)
+            Social_Media_Presence = gr.Number(label="Social Media Presence (0/1)", value=1)
+
+            btn = gr.Button("Predict")
+
+        with gr.Column():
+            output = gr.JSON(label="Prediction Result")
+
+    btn.click(
+        predict_placement_and_domain,
+        inputs=[ssc_percentage, hsc_percentage, undergrad_degree, Graduate_degree_percentage,
+                emp_test_percentage, Internship_Experience_Months, Certifications_Count,
+                Technical_Skills_Score, Soft_Skills_Score, Hackathons_Participated,
+                Resume_Score, Online_Course_Count, Social_Media_Presence],
+        outputs=output
+    )
+
+demo.launch()