python统计分析-主成份分析

#!/usr/bin/env python
# -*- coding:utf-8 -*-

# 


def execute():
    # 
    '''
    载入模块
    '''
    from sklearn.decomposition import PCA
    import numpy as np
    import pandas as pd
    from sqlalchemy import create_engine
    '''
    连接数据库
    '''
    engine = create_engine('mysql+pymysql://root:123123qwe@127.0.0.1:3306/analysis')
    '''
    选择目标数据
    '''
    # 生成数据
    params = {
        "columns": "SUNACTIVITY",
        "n_components": 1,  #

    }
    inputs = {"table": '纯随机性检验'}
    data_sql = 'select ' + params['columns'] + ' from ' + inputs['table']
    data_in = pd.read_sql_query(data_sql, engine)
    print(data_in)

    '''
    主成分分析
    '''
    data_in = data_in.select_dtypes(include=['number'])  # 筛选数值型数据
    n_samples, n_features = data_in.shape
    if not 1 <= int(params['n_components']) <= n_features:
        raise ValueError("\n降维后的维数为%r,该值必须要在[1,%r]之间." % (int(params['n_components']), n_features))

    pca_model = PCA(n_components=int(params['n_components']))
    pca_model.fit(data_in)
    print(pca_model.explained_variance_ratio_)
    print(pca_model.explained_variance_)

    # 执行降维
    data_out = pca_model.transform(data_in)
    columns = list(range(1, int(params['n_components']) + 1))
    columns = ['comp_' + str(i) for i in columns]
    data_out = pd.DataFrame(data_out, columns=columns)
    data_out = np.around(data_out, decimals=4)

    '''
    将结果写出
    '''
    print(data_out)

    '''
    数据示例
        SUNACTIVITY
    0           5.0
    1          11.0
    2          16.0
    3          23.0
    4          36.0
    5          40.4
    6          29.8
    7          15.2
    8           7.5
    9           2.9
10         83.4
11         47.7
12         47.8
13         30.7
14         12.2
15         40.4
16         29.8
17         15.2
18          7.5
19          2.9
20         12.6
[1.]
[394.82661905]
    comp_1
0  -19.619
1  -13.619
2   -8.619
3   -1.619
4   11.381
5   15.781
6    5.181
7   -9.419
8  -17.119
9  -21.719
10  58.781
11  23.081
12  23.181
13   6.081
14 -12.419
15  15.781
16   5.181
17  -9.419
18 -17.119
19 -21.719
20 -12.019
    '''
# 


if __name__ == '__main__':
    execute()