correlation1.py

import pandas as pd
from scipy.stats.stats import pearsonr
import matplotlib.pyplot as plt
import numpy as np

df = pd.read_excel('data_2.xlsx')
print(df)
c = pd.Series(df.columns.values, name='x').tolist()
print(c)

remove_list = ['Year', 'Company', '설립연도']

x_data = []
y_data = []

for x in remove_list:
    c.remove(x)

for i in range(0, len(c)):
    for j in range(i + 1, len(c)):
        r, p_v = pearsonr(df[c[i]], df[c[j]])
        if abs(r) > 0.1:
            x_data.append("{} / {} ".format(c[i], c[j]))
            y_data.append(r)
            print("{}, {} : {}".format(c[i], c[j], r))

z = sorted(zip(x_data,y_data), key=lambda _t: _t[1])

x_sorted = []
y_sorted = []

print(z)
for _z in z:
    x_sorted.append(_z[0])
    y_sorted.append(_z[1])

x_t = np.arange(len(z))
plt.bar(x_t,y_sorted)
plt.xticks(x_t, x_sorted)
plt.show()