import matplotlib.pyplot as plt
import MySQLdb as mdb
import numpy as np
from mpl_toolkits.axes_grid1.inset_locator import inset_axes
from mpl_toolkits.axes_grid1.inset_locator import mark_inset


def graph():
  # 連接數(shù)據(jù)庫
  conn = mdb.connect(host='127.0.0.1', port=3306, user='root', passwd='root', db='alibaba_trace', charset='utf8')

  # 如果使用事務(wù)引擎，可以設(shè)置自動(dòng)提交事務(wù)，或者在每次操作完成后手動(dòng)提交事務(wù)conn.commit()
  conn.autocommit(1) # conn.autocommit(True)

  # 使用cursor()方法獲取操作游標(biāo)
  cursor = conn.cursor()
  # 因該模塊底層其實(shí)是調(diào)用CAPI的，所以，需要先得到當(dāng)前指向數(shù)據(jù)庫的指針。
  try:
    cursor.execute("select machineID, count(id) from batch_instance where machineID != 0 group by machineID")
    records = cursor.fetchall()
    list_records = list(records)

  except:
    import traceback
    traceback.print_exc()
    # 發(fā)生錯(cuò)誤時(shí)回滾
    conn.rollback()
  finally:
    # 關(guān)閉游標(biāo)連接
    cursor.close()
    # 關(guān)閉數(shù)據(jù)庫連接
    conn.close()

  res = []
  res[:] = map(list, list_records)
  machineID = [x[0] for x in res]
  instance_num = [x[1] for x in res]
  print(max(instance_num))
  print(min(instance_num))


  fig = plt.figure()
  ax1 = fig.add_subplot(1, 1, 1)
  # # cdf
  # hist, bin_edges = np.histogram(instance_num, bins=len(np.unique(instance_num)))
  # cdf = np.cumsum(hist / sum(hist))
  # ax1.plot(bin_edges[1:], cdf, color='red', ls='-')
  # ax1.set_xlabel("instance number per machine")
  # ax1.set_ylabel("portion of machine")
  # plt.savefig('../../imgs_mysql/cdf_of_machine_instance.png')

  # # 直方圖
  ax1.hist(instance_num, normed=False, alpha=1.0, bins=100)
  ax1.set_xlabel('instance number per machine')
  ax1.set_ylabel('machine number')
  # cdf 要添加的子圖
  axins = inset_axes(ax1, width=1.5, height=1.5, loc='upper left')
  # ax1 大圖
  # width height分別為子圖的寬和高
  # loc 為子圖在大圖ax1中的相對位置 相應(yīng)的值有
  # upper left
  # lower left
  # lower right
  # right
  # center left
  # center right
  # lower center
  # upper center
  # center
  hist, bin_edges = np.histogram(instance_num, bins=len(np.unique(instance_num)))
  cdf = np.cumsum(hist / sum(hist))
  axins.plot(bin_edges[1:], cdf, color='red', ls='-')
  axins.set_yticks([])
  # axins.set_xlabel("instance number per machine")
  # axins.set_ylabel("portion of machine")

  plt.savefig("../../imgs_mysql/hist_of_machine_instance")
  plt.show()

if __name__ == '__main__':
  graph()