# -*- encoding=utf-8 -*-

import pandas

if __name__ == '__main__':
  pass
  test_stu = pandas.DataFrame(
    {'高數(shù)': [66, 77, 88, 99, 85],
     '大物': [88, 77, 85, 78, 65],
     '英語': [99, 84, 87, 56, 75]},
  )
  print(test_stu)
  stu = pandas.DataFrame(
    {'高數(shù)': [66, 77, 88, 99, 85],
     '大物': [88, 77, 85, 78, 65],
     '英語': [99, 84, 87, 56, 75]},
    index=['小紅', '小李', '小白', '小黑', '小青'] # 指定index索引
  )
  print(stu)

高數(shù) 大物 英語
0 66 88 99
1 77 77 84
2 88 85 87
3 99 78 56
4 85 65 75
  高數(shù) 大物 英語
小紅 66 88 99
小李 77 77 84
小白 88 85 87
小黑 99 78 56
小青 85 65 75

# -*- encoding=utf-8 -*-

import pandas

if __name__ == '__main__':
  pass
  data = pandas.read_csv('data.csv', engine='python') # 使用python分析引擎讀取csv文件
  print(data.head(5)) # 顯示前5行，
  print(data.tail(5)) # 顯示后5行
  print(data) # 顯示所有數(shù)據(jù)
  print(data['height']) # 顯示height列
  print(data[['height', 'weight']]) # 顯示height和weight列
  data.to_csv('write.csv') # 保存到csv文件
  data.to_excel('write.xlsx') # 保存到xlsx文件
  data.info() # 查看數(shù)據(jù)信息(總行數(shù)，有無空缺數(shù)據(jù)，類型)
  print(data.describe()) # (count非空值，mean均值、std標(biāo)準(zhǔn)差、min最小值、max最大值25%50%75%分位數(shù)。)
  data['新增列'] = range(0, len(data)) # 類似字典直接添加即可
  print(data)
  new_data = data.drop('新增列', axis=1, inplace=False)
  # 刪除列,如果inplace為True則在源數(shù)據(jù)刪除，返回None，否則返回新數(shù)據(jù)，不改動源數(shù)據(jù)
  print(new_data)
  data['體重+身高'] = data['height'] + data['weight']
  print(data)
  data['remark'] = data['remark'].str.replace('to', '') # 操作字符串
  print(data['remark'])
  data['birth'] = pandas.to_datetime(data['birth']) # 轉(zhuǎn)為日期類型
  print(data['birth'])

# -*- encoding=utf-8 -*-

import pandas

if __name__ == '__main__':
  pass
  data = pandas.read_csv('data.csv', engine='python') # 使用python分析引擎讀取csv文件
  a = data.iloc[:12, ] # 截取0-12行，列全截
  # print(a)
  b = data.iloc[:, [1, 3]] # 行全截,列1,3
  # print(b)
  c = data.iloc[0:12, 0:4] # 截取行0-12，列0-4
  # print(c)
  d = data['sex'] == 1 # 查看性別為1(男)的
  # print(d)
  f = data.loc[data['sex'] == 1, :] # 查看性別為1(男)的
  # print(f)
  g = data.loc[:, ['weight', 'height']] # 選取身高體重
  # print(g)
  h = data.loc[data['height'].isin([166, 175]), :] # 選取身高166,175的數(shù)據(jù)
  # print(h)
  h1 = data.loc[data['height'].isin([166, 175]), ['weight', 'height']] # 選取身高166,175的數(shù)據(jù)
  # print(h1)
  i = data['height'].mean() # 均值
  j = data['height'].std() # 方差
  k = data['height'].median() # 中位數(shù)
  l = data['height'].min() # 最小值
  m = data['height'].max() # 最大值
  # print(i)
  # print(j)
  # print(k)
  # print(l)
  # print(m)
  n = data.loc[
    (data['height'] > data['height'].mean()) &
    (data['weight'] > data['weight'].mean()),
    :] # 身高大于身高均值，且體重大于體重均值，不能用and要用&如果是或用|
  print(n)

# -*- encoding=utf-8 -*-

import pandas

if __name__ == '__main__':
  pass
  sheet1 = pandas.read_excel('data.xlsx', sheet_name='Sheet1') # 讀取sheet1
  # print(sheet1)
  # print('-------------------------')
  sheet2 = pandas.read_excel('data.xlsx', sheet_name='Sheet2') # 讀取sheet2
  # print(sheet2)
  # print('-------------------------')
  a = pandas.concat([sheet1, sheet2]) # 合并
  # print(a)
  # print('-------------------------')
  b = a.dropna() # 刪除空數(shù)據(jù)nan，有nan的就刪除
  # print(b)
  # print('-------------------------')
  b1 = a.dropna(subset=['weight']) # 刪除指定列的空數(shù)據(jù)nan
  # print(b1)
  # print('-------------------------')
  c = b.drop_duplicates() # 刪除重復(fù)數(shù)據(jù)
  # print(c)
  # print('-------------------------')
  d = b.drop_duplicates(subset=['weight']) # 刪除指定列的重復(fù)數(shù)據(jù)
  # print(d)
  # print('-------------------------')
  e = b.drop_duplicates(subset=['weight'], keep='last') # 刪除指定列的重復(fù)數(shù)據(jù),保存最后一個相同數(shù)據(jù)
  # print(e)
  # print('-------------------------')
  f = a.sort_values(['weight'], ascending=False) # 從大到小排序weight
  # print(f)
  g = c.groupby(['sex']).sum() # 根據(jù)sex分組，再求和
  # print(g)
  g1 = c.groupby(['sex'], as_index=False).sum() # 根據(jù)sex分組，再求和，但sex不作為索引
  # print(g1)
  g2 = c.groupby(['sex', 'weight']).sum() # 根據(jù)sex分組后再根據(jù)weight分組，再求和
  # print(g2)
  h = pandas.cut(c['weight'], bins=[80, 90, 100, 150, 200], ) # 根據(jù)區(qū)間分割體重
  print(h)
  # print('-------------------------')
  c['根據(jù)體重分割'] = h # 會有警告，未解決，但不影響結(jié)果
  print(c)