#-*- encoding=utf-8 -*-
import datetime
import numpy as np
import matplotlib.pyplot as plt
import matplotlib
zhfont1 = matplotlib.font_manager.FontProperties(fname='C:\Windows\Fonts\simsun.ttc')


# 按照固定區(qū)間長度繪制頻率分布直方圖
# bins_interval 區(qū)間的長度
# margin    設(shè)定的左邊和右邊空留的大小
def probability_distribution(data, bins_interval=1, margin=1):
  bins = range(min(data), max(data) + bins_interval - 1, bins_interval)
  print(len(bins))
  for i in range(0, len(bins)):
    print(bins[i])
  plt.xlim(min(data) - margin, max(data) + margin)
  plt.title("probability-distribution")
  plt.xlabel('Interval')
  plt.ylabel('Probability')
  plt.hist(x=data, bins=bins, histtype='bar', color=['r'])
  plt.show()

#-*- encoding=utf-8 -*-
import datetime
import numpy as np
import matplotlib.pyplot as plt
import matplotlib
zhfont1 = matplotlib.font_manager.FontProperties(fname='C:\Windows\Fonts\simsun.ttc'

# 自己給定區(qū)間，小于區(qū)間左端點和大于區(qū)間右端點的統(tǒng)一做處理，對于數(shù)據(jù)分布不均很的情況處理較友好
# bins   自己設(shè)定的區(qū)間數(shù)值列表
# margin  設(shè)定的左邊和右邊空留的大小
# label   右上方顯示的圖例文字
"""e
  import numpy as np
  data = np.random.normal(0, 1, 1000)
  bins = np.arange(-5, 5, 0.1)
  probability_distribution_extend(data=data, bins=bins)
"""
def probability_distribution_extend(data, bins, margin=1, label='Distribution'):
  bins = sorted(bins)
  length = len(bins)
  intervals = np.zeros(length+1)
  for value in data:
    i = 0
    while i < length and value >= bins[i]:
      i += 1
    intervals[i] += 1
  intervals = intervals / float(len(data))
  plt.xlim(min(bins) - margin, max(bins) + margin)
  bins.insert(0, -999)
  plt.title("probability-distribution")
  plt.xlabel('Interval')
  plt.ylabel('Probability')
  plt.bar(bins, intervals, color=['r'], label=label)
  plt.legend()
  plt.show()

if __name__ == '__main__':
  data = [1,4,6,7,8,9,11,11,12,12,13,13,16,17,18,22,25]
  probability_distribution(data=data, bins_interval=5,margin=0)