python【大數據分析】Pandas（06）

# serise 序列 創建
import pandas as pd
import numpy as np

s = pd.Series([9, 'zheng', 'beijing', 128])

print(s)
print(s[0:2])

# serise 序列 操作
import pandas as pd
import numpy as np

s = pd.Series([9, 'zheng', 'beijing', 128, 'usa', 990], index=[1,2,3,'e','f','g'])

sum = s[1:3] + s[1:3]
sum1 = s[1:4] + s[1:4]
sum2 = s[1:3] + s[1:4]
sum3 = s[:3] + s[1:]

print(sum)
print(sum1)
print(sum2)
print(sum3)

# serise 序列 查找
import pandas as pd
import numpy as np

s = {"ton": 20, "mary": 18, "jack": 19, "jim": 22, "lj": 24, "car": None}

sa = pd.Series(s, name="age")

print(sa[sa > 19])

# 中位數
import pandas as pd
import numpy as np
 
s = {"ton": 20, "mary": 18, "jack": 19, "jim": 22, "lj": 24, "car": None}
 
sa = pd.Series(s, name="age")
 
print(sa.median())  # 20

# 判斷是否大於中位數
import pandas as pd
import numpy as np
 
s = {"ton": 20, "mary": 18, "jack": 19, "jim": 22, "lj": 24, "car": None}
 
sa = pd.Series(s, name="age")
 
print(sa>sa.median())

# 找出大於中位數的數
import pandas as pd
import numpy as np
 
s = {"ton": 20, "mary": 18, "jack": 19, "jim": 22, "lj": 24, "car": None}
 
sa = pd.Series(s, name="age")
 
print(sa[sa > sa.median()])

# 中位數
import pandas as pd
import numpy as np
 
s = {"ton": 20, "mary": 18, "jack": 19, "jim": 22, "lj": 24, "car": None}
 
sa = pd.Series(s, name="age")
 
more_than_midian = sa>sa.median()
 
print(more_than_midian)
 
print('---------------------')
 
print(sa[more_than_midian])

# Series賦值
import pandas as pd
import numpy as np
 
s = {"ton": 20, "mary": 18, "jack": 19, "jim": 22, "lj": 24, "car": None}
 
sa = pd.Series(s, name="age")
 
print(s)
 
print('----------------')
 
sa['ton'] = 99
 
print(sa)

# 滿足條件的統一賦值
import pandas as pd
import numpy as np
 
s = {"ton": 20, "mary": 18, "jack": 19, "jim": 22, "lj": 24, "car": None}
 
sa = pd.Series(s, name="age")
 
print(s) # 打印原字典
 
print('---------------------')   # 分割線
 
sa[sa>19] = 88 # 將所有大於19的同一改爲88
 
print(sa) # 打印更改之後的數據
 
print('---------------------')   # 分割線
 
print(sa / 2) # 將所有數據除以2

# DataFrame 矩陣
import pandas as pd
import numpy as np

test_dict = {'id':[1,2,3,4,5,6],'name':['Alice','Bob','Cindy','Eric','Helen','Grace '],'math':[90,89,99,78,97,93],'english':[89,94,80,94,94,90]}
#[1].直接寫入參數test_dict
test_dict_df = pd.DataFrame(test_dict)
#[2].字典型賦值
# test_dict_df = pd.DataFrame(data=test_dict)
# test_dict_df = pd.DataFrame.from_dict(test_dict)
test_dict_df = pd.DataFrame({'id':1,'name':'Alice'},pd.Index(range(3)))
print(test_dict_df)

pandas 是主力工具 在此只簡單介紹 後面將頻繁介紹