# -*- coding: utf-8 -*-
"""Untitled32.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1p0-6f2W12BK0UkzE_Pmi-_unUccbz-w-
"""

import tensorflow as tf
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
import numpy as np

# Step 1: Load the Iris dataset
iris = load_iris()
X = iris.data  # Features: Sepal/Petal length/width
y = iris.target.reshape(-1, 1)  # Labels: Classes 0, 1, 2

# Step 2: One-hot encode the labels
encoder = OneHotEncoder(sparse_output=False)
y_one_hot = encoder.fit_transform(y)

# Step 3: Split into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y_one_hot, test_size=0.2, random_state=42)

# Step 4: Build the TensorFlow model
model = tf.keras.Sequential([
    tf.keras.layers.InputLayer(input_shape=(X.shape[1],)),  # Input layer (4 features)
    tf.keras.layers.Dense(10, activation='relu'),          # Hidden layer (10 units)
    tf.keras.layers.Dense(3, activation='softmax')         # Output layer (3 classes)
])

# Step 5: Compile the model
model.compile(optimizer='adam',
              loss='categorical_crossentropy',
              metrics=['accuracy'])

# Step 6: Train the model
history = model.fit(X_train, y_train, epochs=100, batch_size=16, validation_split=0.1, verbose=1)

# Step 7: Evaluate the model
loss, accuracy = model.evaluate(X_test, y_test)
print(f"Test Loss: {loss:.4f}")
print(f"Test Accuracy: {accuracy:.4f}")

# Step 8: Make Predictions
predictions = model.predict(X_test)
predicted_classes = np.argmax(predictions, axis=1)
true_classes = np.argmax(y_test, axis=1)

print(f"True Labels: {true_classes}")
print(f"Predicted Labels: {predicted_classes}")