从入门到实战详解Python如何做数据预测

from prophet import Prophet
import pandas as pd

# 数据格式：必须有 ds（日期）和 y（数值）两列
df = pd.read_csv('sales.csv')
df.columns = ['ds', 'y']

model = Prophet()
model.fit(df)

future = model.make_future_dataframe(periods=30)  # 预测未来30天
forecast = model.predict(future)

model.plot(forecast)  # 直接出图

import xgboost as xgb
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_error

# 假设 df 已准备好，X是特征，y是房价
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = xgb.XGBRegressor(
    n_estimators=500,
    learning_rate=0.05,
    max_depth=6,
    random_state=42
)
model.fit(X_train, y_train)

preds = model.predict(X_test)
print(f"MAE: {mean_absolute_error(y_test, preds):.2f}")

from sklearn.ensemble import RandomForestClassifier

model = RandomForestClassifier(n_estimators=200, random_state=42)
model.fit(X_train, y_train)

# 输出概率（比单纯的0/1更有价值）
proba = model.predict_proba(X_test)[:, 1]

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error, r2_score
# 1. 加载数据
df = pd.read_csv('data.csv')
X = df[['X1', 'X2']]
y = df['y']
# 2. 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# 3. 创建并训练模型
model = LinearRegression()
model.fit(X_train, y_train)
# 4. 预测
y_pred = model.predict(X_test)
# 5. 评估
print(f"MAE: {mean_absolute_error(y_test, y_pred):.2f}")
print(f"R²: {r2_score(y_test, y_pred):.2f}")
# 6. 对新数据预测
new_data = pd.DataFrame({'X1': [10, 20], 'X2': [5, 15]})
pred_new = model.predict(new_data)
print(pred_new)

import pandas as pd
import matplotlib.pyplot as plt
from statsmodels.tsa.arima.model import ARIMA
from statsmodels.tsa.stattools import adfuller
# 假设 df 包含日期和销售额
df = pd.read_csv('sales.csv', parse_dates=['date'], index_col='date')
series = df['sales']
# 平稳性检验（差分）
result = adfuller(series)
if result[1] > 0.05:
    series = series.diff().dropna()
# 训练 ARIMA 模型 (p,d,q 需通过 ACF/PACF 或自动选择)
model = ARIMA(series, order=(1,1,1))
fitted = model.fit()
# 预测未来 30 步
forecast = fitted.forecast(steps=30)
print(forecast)
# 可视化
plt.plot(series)
plt.plot(forecast, color='red')
plt.show()

import xgboost as xgb
from sklearn.ensemble import RandomForestRegressor
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
# 数据准备
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# 构建包含标准化和模型的流水线
pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('xgb', xgb.XGBRegressor(n_estimators=100, learning_rate=0.1, random_state=42))
])
pipeline.fit(X_train, y_train)
y_pred = pipeline.predict(X_test)
# 特征重要性
feature_importance = pipeline.named_steps['xgb'].feature_importances_