机器学习

数据导入

import pandas as pd
from sklearn.datasets import load_iris
​
# 1. Read in the dataset
# Using the Iris dataset from sklearn for demonstration
data = load_iris()
df = pd.DataFrame(data.data, columns=data.feature_names)
df['target'] = data.target
​
df.head()

分割数据集

from sklearn.model_selection import train_test_split
​
X = df.drop('target', axis=1)  # Features
y = df['target']              # Target variable
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

训练，fit

from sklearn.ensemble import RandomForestClassifier
​
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)

模型评估

from sklearn.metrics import precision_score, recall_score
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)
​
train_precision = precision_score(y_train, y_train_pred, average='macro')
train_recall = recall_score(y_train, y_train_pred, average='macro')
test_precision = precision_score(y_test, y_test_pred, average='macro')
test_recall = recall_score(y_test, y_test_pred, average='macro')
​
print("\nEvaluation Metrics:")
print(f"Train Precision: {train_precision:.2f}, Train Recall: {train_recall:.2f}")
print(f"Test Precision: {test_precision:.2f}, Test Recall: {test_recall:.2f}")

使用模型并且保存数据

# 5. Make Predictions
predictions = model.predict(X_test)
predictions
​
 Save predictions to a CSV file
​
# results = pd.DataFrame({
#     'True Labels': y_test,
#     'Predicted Labels': predictions
# })
# results.to_csv('predictions.csv', index=False)