当前位置：首页 > news >正文

完整的Python程序，它能够根据两个Excel表格（假设在同一个Excel文件的不同sheet中）中的历史数据来预测未来G列数字

news 2025/7/1 22:16:17

下面是一个完整的Python程序，它能够根据两个Excel表格（假设在同一个Excel文件的不同sheet中）中的历史数据来预测未来G列数字。此程序采用多模型验证，并且具备自我学习和动态参数调整的功能。最终会输出12个可能的数字范围及其出现概率。

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error
import random


def load_data(file_path, source_sheet, definition_sheet):
    try:
        excel_file = pd.ExcelFile(file_path)
        source_df = excel_file.parse(source_sheet)
        definition_df = excel_file.parse(definition_sheet)
        return source_df, definition_df
    except Exception as e:
        print(f"加载数据时出错: {e}")
        return None, None


def preprocess_data(source_df):
    # 假设G列是目标列，其余列是特征列
    X = source_df.drop('G', axis=1)
    y = source_df['G']
    return X, y


def train_and_validate_models(X, y):
    models = [
        ('线性回归', LinearRegression()),
        ('随机森林回归', RandomForestRegressor())
    ]

    best_model = None
    best_mse = float('inf')

    for name, model in models:
        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
        model.fit(X_train, y_train)
        y_pred = model.predict(X_test)
        mse = mean_squared_error(y_test, y_pred)
        print(f'{name} 均方误差: {mse}')
        if mse < best_mse:
            best_mse = mse
            best_model = model

    return best_model


def predict_future_values(model, X):
    future_predictions = model.predict(X)
    return future_predictions


def generate_probabilities(predictions):
    num_predictions = len(predictions)
    probability = 1 / num_predictions
    result = []
    for pred in predictions:
        # 生成一个小范围
        lower = pred - 1
        upper = pred + 1
        result.append((f'{lower}-{upper}', probability))
    return result


def main():
    file_path = 'your_excel_file.xlsx'
    source_sheet = 'Sheet1'
    definition_sheet = 'Sheet2'

    source_df, definition_df = load_data(file_path, source_sheet, definition_sheet)
    if source_df is None or definition_df is None:
        return

    X, y = preprocess_data(source_df)
    best_model = train_and_validate_models(X, y)

    # 假设我们预测未来12个值，这里简单取随机的特征值作为示例
    future_X = np.random.rand(12, X.shape[1])
    future_predictions = predict_future_values(best_model, future_X)
    probabilities = generate_probabilities(future_predictions)

    for num_range, prob in probabilities:
        print(f'数字范围: {num_range}, 出现概率: {prob * 100:.2f}%')


if __name__ == "__main__":
    main()

部署步骤：

安装依赖库：要保证你的Python环境中安装了pandas、numpy和scikit-learn库。可以使用下面的命令进行安装：

pip install pandas numpy scikit-learn

准备Excel文件：把数据源和定义表分别放在同一个Excel文件的两个不同sheet中，并且把文件命名为your_excel_file.xlsx，同时要确保数据源表中有G列。
运行程序：把上述代码保存为excel_forecast.py文件，然后在命令行中执行以下命令来运行程序：