thecolleges

college predictor.py

@@ -0,0 +1,85 @@
+import pandas as pd
+import numpy as np
+import gradio as gr
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+from sklearn.ensemble import RandomForestClassifier
+import joblib
+
+# Load and preprocess data
+def load_and_preprocess_data(filename):
+    df = pd.read_csv(filename)
+    
+    label_encoders = {}
+    for col in ["College Name", "Category", "Gender", "Branch", "Region"]:
+        le = LabelEncoder()
+        df[col] = le.fit_transform(df[col])
+        label_encoders[col] = le
+    
+    X = df[["Category", "Gender", "Opening Rank", "Closing Rank", "Region"]]
+    y_college_branch = df[["College Name", "Branch"]]
+    
+    return X, y_college_branch, label_encoders, df
+
+filename = "AP_EAMCET_Engineering_10000 (1).csv"
+X, y_college_branch, label_encoders, df = load_and_preprocess_data(filename)
+
+# Train model
+def train_model(X, y):
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    model = RandomForestClassifier(n_estimators=100, random_state=42)
+    model.fit(X_train, y_train)
+    return model
+
+college_branch_model = train_model(X, y_college_branch)
+
+joblib.dump(college_branch_model, "college_branch_model.pkl")
+joblib.dump(label_encoders, "label_encoders.pkl")
+
+# Prediction function
+def predict_colleges(category, gender, rank, region):
+    # Load label encoders
+    label_encoders = joblib.load("label_encoders.pkl")
+    
+    # Transform input values using label encoders
+    try:
+        category_enc = label_encoders["Category"].transform([category])[0]
+        gender_enc = label_encoders["Gender"].transform([gender])[0]
+        region_enc = label_encoders["Region"].transform([region])[0]
+    except ValueError:
+        return "Invalid input values. Please select valid options."
+    
+    # Filter the dataset based on encoded values
+    filtered_df = df[
+        (df["Category"] == category_enc) &
+        (df["Gender"] == gender_enc) &
+        (df["Opening Rank"] <= rank) &
+        (df["Closing Rank"] >= rank) &
+        (df["Region"] == region_enc)
+    ]
+    
+    if filtered_df.empty:
+        return "No matching colleges found."
+    
+    # Decode college names and branches
+    filtered_df["College Name"] = label_encoders["College Name"].inverse_transform(filtered_df["College Name"].values)
+    filtered_df["Branch"] = label_encoders["Branch"].inverse_transform(filtered_df["Branch"].values)
+    
+    result = filtered_df[["College Name", "Branch"]].drop_duplicates().to_string(index=False)
+    return result
+
+# Gradio Interface
+demo = gr.Interface(
+    fn=predict_colleges,
+    inputs=[
+        gr.Dropdown(choices=["OC", "BC", "SC", "ST"], label="Category"),
+        gr.Radio(choices=["Male", "Female"], label="Gender"),
+        gr.Number(label="Rank"),
+        gr.Dropdown(choices=["AU", "SV"], label="Region")
+    ],
+    outputs="text",
+    title="AP EAMCET College Predictor",
+    description="Enter your details to predict all possible colleges and branches based on your rank."
+)
+
+demo.launch()