How to Build a Machine Learning Model from Scratch in Python

bash
pip install numpy pandas scikit-learn matplotlib seaborn

python
import pandas as pd
import numpy as np
from sklearn.datasets import load_iris

# Load the classic Iris dataset
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df['target'] = iris.target

# Explore the data
print(df.head())
print(df.describe())
print(df['target'].value_counts())

python
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# Split into features and target
X = df.drop('target', axis=1)
y = df['target']

# Split into training and testing sets (80/20)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

# Scale features to have zero mean and unit variance
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

python
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report

# Initialize and train the model
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train_scaled, y_train)

# Make predictions
y_pred = model.predict(X_test_scaled)

# Evaluate
print(f"Accuracy: {accuracy_score(y_test, y_pred):.4f}")
print(classification_report(y_test, y_pred))

python
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
import seaborn as sns

cm = confusion_matrix(y_test, y_pred)
plt.figure(figsize=(8, 6))
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')
plt.title('Confusion Matrix')
plt.ylabel('Actual')
plt.xlabel('Predicted')
plt.savefig('confusion_matrix.png')