preprc.py

# ==============================
# Step 1: Import Libraries
# ==============================
import pandas as pd
import numpy as np

from sklearn.preprocessing import LabelEncoder, StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix


# ==============================
# Step 2: Create Dataset
# ==============================
data = {
    "Hours_Studied": [5, 2, np.nan, 8],
    "Attendance": [80, np.nan, 60, 90],
    "Result": ["Pass", "Fail", "Fail", "Pass"]
}

df = pd.DataFrame(data)
print("Original Data:\n", df)


# ==============================
# Step 3: Handle Missing Values
# ==============================
df['Hours_Studied']=df["Hours_Studied"].fillna(df["Hours_Studied"].mean(), inplace=True)
df["Attendance"]=df["Attendance"].fillna(df["Attendance"].mean(), inplace=True)

print("\nAfter Handling Missing Values:\n", df)

 
# ==============================
# Step 4: Encode Target Variable
# ==============================
le = LabelEncoder()
df["Result"] = le.fit_transform(df["Result"])

print("\nAfter Encoding Target:\n", df)


# ==============================
# Step 5: Feature Scaling
# ==============================
scaler = StandardScaler()
df[["Hours_Studied", "Attendance"]] = scaler.fit_transform(
    df[["Hours_Studied", "Attendance"]]
)

print("\nAfter Feature Scaling:\n", df)


# ==============================
# Step 6: Split Data
# ==============================
X = df[["Hours_Studied", "Attendance"]]
y = df["Result"]

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25, random_state=42
)


# ==============================
# Step 7: Train Model
# ==============================
model = LogisticRegression()
model.fit(X_train, y_train)


# ==============================
# Step 8: Prediction
# ==============================
y_pred = model.predict(X_test)

print("\nPredicted Values:", y_pred)
print("Actual Values   :", y_test.values)


# ==============================
# Step 9: Evaluation
# ==============================
accuracy = accuracy_score(y_test, y_pred)
cm = confusion_matrix(y_test, y_pred)

print("\nModel Accuracy:", accuracy)
print("Confusion Matrix:\n", cm)