import os.path

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

csv_path = r"XXX.csv"
save_fig_path = os.path.join(os.path.split(csv_path)[0], "metrics_cdf.png")

# 從CSV讀取數(shù)據(jù)
data = pd.read_csv(csv_path)['XXX']

# 計算CDF
data_sorted = np.sort(data)[::-1]
cdf = np.arange(1, len(data_sorted)+1) / len(data_sorted)

# 繪制CDF圖
plt.plot(data_sorted, cdf, linewidth=2)  # marker='.',
plt.xlabel('Value')
plt.ylabel('CDF')
plt.xticks(np.arange(0, 1.1, 0.1))
plt.yticks(np.arange(0, 1.1, 0.1))
plt.title('Cumulative Distribution Function (CDF)')
plt.grid(True)
plt.savefig(save_fig_path)
plt.show()

plt.plot(x_data, y_data, marker='o')

import numpy as np
import statsmodels.api as sm
import matplotlib.pyplot as plt

data = []
ecdf = sm.distributions.ECDF(data)
x = np.linspace(min(data), max(data))
y = ecdf(x)

for a, b in zip(x, y):
    print(a, b)

plt.plot(x, y, linewidth='5', label='XX', color="green", linestyle="dashed")

plt.xlabel('XX', fontsize = 15)
plt.ylabel('CDF', fontsize=15)

plt.xlim(0, 1500)
plt.ylim(0, 1)

plt.xticks(fontsize=14)
plt.yticks(fontsize=14)

# plt.legend(loc='lower right', fontsize = 17) % 當有多個CDF曲線，對曲線進行標注

plt.show()

import matplotlib.pyplot as plt
import numpy as np
from scipy import stats
data = np.random.normal(size=1000)
plt.plot(sorted(data), stats.norm.cdf(sorted(data)))
plt.show()