Python Pandas数据分析工具用法实例

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

import pandas

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

高数 大物 英语
0 66 88 99
1 77 77 84
2 88 85 87
3 99 78 56
4 85 65 75
  高数 大物 英语
小红 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分析引擎读取csv文件
  print(data.head(5)) # 显示前5行，
  print(data.tail(5)) # 显示后5行
  print(data) # 显示所有数据
  print(data['height']) # 显示height列
  print(data[['height', 'weight']]) # 显示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() # 查看数据信息(总行数，有无空缺数据，类型)
  print(data.describe()) # (count非空值，mean均值、std标准差、min最小值、max最大值25%50%75%分位数。)
  data['新增列'] = range(0, len(data)) # 类似字典直接添加即可
  print(data)
  new_data = data.drop('新增列', axis=1, inplace=False)
  # 删除列,如果inplace为True则在源数据删除，返回None，否则返回新数据，不改动源数据
  print(new_data)
  data['体重+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']) # 转为日期类型
  print(data['birth'])

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

import pandas

if __name__ == '__main__':
  pass
  data = pandas.read_csv('data.csv', engine='python') # 使用python分析引擎读取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 # 查看性别为1(男)的
  # print(d)
  f = data.loc[data['sex'] == 1, :] # 查看性别为1(男)的
  # print(f)
  g = data.loc[:, ['weight', 'height']] # 选取身高体重
  # print(g)
  h = data.loc[data['height'].isin([166, 175]), :] # 选取身高166,175的数据
  # print(h)
  h1 = data.loc[data['height'].isin([166, 175]), ['weight', 'height']] # 选取身高166,175的数据
  # print(h1)
  i = data['height'].mean() # 均值
  j = data['height'].std() # 方差
  k = data['height'].median() # 中位数
  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，且体重大于体重均值，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') # 读取sheet1
  # print(sheet1)
  # print('-------------------------')
  sheet2 = pandas.read_excel('data.xlsx', sheet_name='Sheet2') # 读取sheet2
  # print(sheet2)
  # print('-------------------------')
  a = pandas.concat([sheet1, sheet2]) # 合并
  # print(a)
  # print('-------------------------')
  b = a.dropna() # 删除空数据nan，有nan的就删除
  # print(b)
  # print('-------------------------')
  b1 = a.dropna(subset=['weight']) # 删除指定列的空数据nan
  # print(b1)
  # print('-------------------------')
  c = b.drop_duplicates() # 删除重复数据
  # print(c)
  # print('-------------------------')
  d = b.drop_duplicates(subset=['weight']) # 删除指定列的重复数据
  # print(d)
  # print('-------------------------')
  e = b.drop_duplicates(subset=['weight'], keep='last') # 删除指定列的重复数据,保存最后一个相同数据
  # print(e)
  # print('-------------------------')
  f = a.sort_values(['weight'], ascending=False) # 从大到小排序weight
  # print(f)
  g = c.groupby(['sex']).sum() # 根据sex分组，再求和
  # print(g)
  g1 = c.groupby(['sex'], as_index=False).sum() # 根据sex分组，再求和，但sex不作为索引
  # print(g1)
  g2 = c.groupby(['sex', 'weight']).sum() # 根据sex分组后再根据weight分组，再求和
  # print(g2)
  h = pandas.cut(c['weight'], bins=[80, 90, 100, 150, 200], ) # 根据区间分割体重
  print(h)
  # print('-------------------------')
  c['根据体重分割'] = h # 会有警告，未解决，但不影响结果
  print(c)