File size: 5,814 Bytes
3816915
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
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()