Machine Learning: 机器学习简介与Python生态 — 从概念到工具链的完整入门指南

# A simple ML prediction workflow
import pandas as pd
from sklearn.linear_model import LinearRegression

# Load historical sales data
data = pd.read_csv("sales_history.csv")
X = data[["ad_spend", "traffic", "last_month_sales"]]
y = data["monthly_revenue"]

# Train model and predict
model = LinearRegression()
model.fit(X, y)
next_month_pred = model.predict([[50000, 120000, 380000]])
print(f"Predicted revenue: {next_month_pred[0]:.0f} USD")

# Check installed ML packages and versions
import importlib

packages = ["numpy", "pandas", "matplotlib", "sklearn", "torch", "xgboost", "mlflow"]

for pkg in packages:
    try:
        mod = importlib.import_module(pkg)
        version = getattr(mod, "__version__", "unknown")
        print(f"{pkg:15s} : {version}")
    except ImportError:
        print(f"{pkg:15s} : NOT INSTALLED")

numpy           : 1.26.4
pandas          : 2.2.0
matplotlib      : 3.8.3
sklearn         : 1.4.0
torch           : 2.2.0
xgboost         : 2.0.3
mlflow          : 2.10.0

# Install core ML packages via conda
conda create -n ml-env python=3.11 -y
conda activate ml-env
conda install numpy pandas matplotlib scikit-learn -y
conda install pytorch torchvision cpuonly -c pytorch -y
pip install xgboost lightgbm mlflow seaborn jupyter

# 命令执行成功

# Create and activate ML environment
conda create -n salespredict python=3.11 -y
conda activate salespredict

# Install Jupyter and kernel
pip install jupyter
python -m ipykernel install --user --name salespredict --display-name "SalesPredict"

# Launch Jupyter
jupyter notebook

# 命令执行成功

# Full environment check for SalesPredict project
import sys
print(f"Python version: {sys.version}")
print(f"Python path: {sys.executable}")

import numpy as np
import pandas as pd
import sklearn
print(f"NumPy version: {np.__version__}")
print(f"Pandas version: {pd.__version__}")
print(f"Scikit-learn version: {sklearn.__version__}")

# Quick functionality test
arr = np.array([1, 2, 3, 4, 5])
print(f"NumPy array mean: {arr.mean()}")
df = pd.DataFrame({"sales": [100, 200, 300]})
print(f"Pandas DataFrame:\n{df}")

# 执行成功

# Explore the SalesPredict dataset structure
import pandas as pd

# Load sample data
df = pd.read_csv("https://example.com/salespredict_sample.csv")
print(f"Dataset shape: {df.shape}")
print(f"\nColumn types:\n{df.dtypes}")
print(f"\nBasic statistics:\n{df.describe()}")
print(f"\nDate range: {df['date'].min()} to {df['date'].max()}")
print(f"Total revenue: {df['revenue'].sum() / 1e6:.1f} million USD")

# 执行成功

# End-to-end mini workflow: predict house prices
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error

# Step 1: Load data
data = fetch_california_housing()
X, y = data.data, data.target

# Step 2: Split train/test
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

# Step 3: Train model
model = RandomForestRegressor(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Step 4: Evaluate
predictions = model.predict(X_test)
mae = mean_absolute_error(y_test, predictions)
print(f"MAE: {mae:.4f} (in 100k USD)")
print(f"Feature importances: {dict(zip(data.feature_names, model.feature_importances_))}")

MAE: 0.3285 (in 100k USD)
Feature importances: {'MedInc': 0.524..., 'HouseAge': 0.053..., ...}