python——因子分析-汇总完整版.pdf

python——因⼦分析 因⼦分析⽤Python做的⼀个典型例⼦ ⼀、实验⽬的 采⽤合适的数据分析⽅法对下⾯的题进⾏解答 ⼆、实验要求 采⽤因⼦分析⽅法，根据48位应聘者的15项指标得分，选出6名最优秀的应聘者。 三、代码 import pandas as pd import numpy as np import math as math import numpy as np from numpy import * from scipy.stats import bartlett from factor_analyzer import * import numpy.linalg as nl from sklearn.cluster import KMeans from matplotlib import cm import matplotlib.pyplot as plt def main(): df=pd.read_csv(./data/applicant.csv) # print(df) df2=df.copy() print(\n原始数据:\n,df2) del df2[ID] # print(df2) # ⽪尔森相关系数 df2_corr=df2.corr() print(\n相关系数:\n,df2_corr) #热⼒图 cmap = cm.Blues # cmap = cm.hot_r fig=plt.figure() ax=fig.add_subplot(111) map = ax.imshow(df2_corr, interpolation=nearest, cmap=cmap, vmin=0, vmax=1) plt.title(correlation coefficient--headmap) ax.set_yticks(range(len(df2_corr.columns))) ax.set_yticklabels(df2_corr.columns) ax.set_xticks(range(len(df2_corr))) ax.set_xticklabels(df2_corr.columns) plt.colorbar(map) plt.show() # KMO测度 def kmo(dataset_corr): corr_inv = np.linalg.inv(dataset_corr) nrow_inv_corr, ncol_inv_corr = dataset_corr.shape A = np.ones((nrow_inv_corr, ncol_inv_corr)) for i in range(0, nrow_inv_corr, 1): for j in range(i, ncol_inv_corr, 1): A[i, j] = -(corr_inv[i, j]) / (math.sqrt(corr_inv[i, i] * corr_inv[j, j])) A[j, i] = A[i, j] dataset_corr = np.asarray(dataset_corr) kmo_num = np.sum(np.square(dataset_corr)) - np.sum(np.square(np.diagonal(A))) kmo_denom = kmo_num + np.sum(np.square(A)) - np.sum(np.square(np.diagonal(A))) kmo_value = kmo_num / kmo_denom return kmo_value print(\nKMO测度:, kmo(df2_corr)) # 巴特利特球形检验 df2_corr1 = df2_corr.values print(\n 巴特利特球形检验:, bartlett(df2_corr1[0], df2_corr1[1], df2_