data_classifer.py

# =========================================================
# PROJECT 2: DATA CLASSIFICATION USING AI
# DecodeLabs Industrial Training Project
# =========================================================

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

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix

# =========================================================
# Step 2: Load Dataset
# =========================================================

# Loading Iris Dataset
iris = load_iris()

# Creating DataFrame
data = pd.DataFrame(iris.data, columns=iris.feature_names)

# Adding Target Column
data['target'] = iris.target

# Display first 5 rows
print("First 5 Rows of Dataset:\n")
print(data.head())

# =========================================================
# Step 3: Understand Dataset
# =========================================================

print("\nDataset Information:\n")
print(data.info())

print("\nDataset Description:\n")
print(data.describe())

print("\nChecking Missing Values:\n")
print(data.isnull().sum())

# =========================================================
# Step 4: Split Features and Labels
# =========================================================

X = data.iloc[:, :-1]   # Features
y = data['target']      # Target labels

# =========================================================
# Step 5: Split Dataset into Training and Testing
# =========================================================

X_train, X_test, y_train, y_test = train_test_split(
    X,
    y,
    test_size=0.2,
    random_state=42
)

print("\nTraining Data Shape:", X_train.shape)
print("Testing Data Shape:", X_test.shape)

# =========================================================
# Step 6: Feature Scaling
# =========================================================

scaler = StandardScaler()

X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# =========================================================
# Step 7: Apply Classification Algorithm
# =========================================================

# Creating KNN Classifier
model = KNeighborsClassifier(n_neighbors=3)

# Train Model
model.fit(X_train, y_train)

# =========================================================
# Step 8: Make Predictions
# =========================================================

y_pred = model.predict(X_test)

print("\nPredicted Values:\n")
print(y_pred)

# =========================================================
# Step 9: Evaluate Model
# =========================================================

accuracy = accuracy_score(y_test, y_pred)

print("\nModel Accuracy:")
print(accuracy * 100, "%")

print("\nClassification Report:\n")
print(classification_report(y_test, y_pred))

print("\nConfusion Matrix:\n")
print(confusion_matrix(y_test, y_pred))

# =========================================================
# Step 10: Test with New Custom Data
# =========================================================

# Example flower measurements
# [sepal length, sepal width, petal length, petal width]

new_data = [[5.1, 3.5, 1.4, 0.2]]

# Scale new data
new_data = scaler.transform(new_data)

# Predict class
prediction = model.predict(new_data)

print("\nPrediction for New Data:", prediction)

# Convert numeric prediction to flower name
flower_name = iris.target_names[prediction][0]

print("Predicted Flower Name:", flower_name)

# =========================================================
# PROJECT COMPLETED
# =========================================================