pandas(Series、DataFrame)

import pandas as pd

#Series的构成和相关方法
t1 = pd.Series([1,2,3,4,5,6])
print(t1)

#t2 = pd.Series([1,2,3,4,5,6],index=['a','b','c','d','e','f'])
t2 = pd.Series([1,2,3,4,5,6],index=list('abcdef'))
print(t2)

#字典创建：键为索引，值为值
dict1 = {'name':'xiaohong','age':30,"tel":10086}
t3 = pd.Series(dict1)
print(t3)
print(t3.dtype)

#Series的切片和索引
print(t3['name'])
print(t3[0])
print(t3[:2])
print(t3[[1,2]])
print(t2[t2>3])

#Series的index和values方法
print(t3.index)
print('*'*100)
for i in t3.index:
    print(i)
print(list(t3.index))

print(type(t3.values))

import pandas as pd
from  pymongo import MongoClient

client = MongoClient()
collection = client["douban"]["tv1"]
data = list(collection.find())
t1 = data[0]
t1 = pd.Series(t1)
print(t1)

切片索引

import pandas as pd

> 这里是引用

df = pd.read_csv("./dogNames2.csv")
#print(df.head())
#print(df.info())

#dataFrame中的排序方法
df = df.sort_values(by="Count_AnimalName",ascending=False)
#print(df.head(5))

#pandas中的切片和索引
#pandas取行或者列的注意事项：
#-方括号写数字，表示对行进行操作
#-方括号写字符串，表示对列进行操作
#-同时存在则是取数字行的字符串的那一列

print(df[20:])
print(df[:20]["Row_Labels"])
print("*"*100)
print(df["Row_Labels"][:20])

import pandas as pd
import numpy as np
df = pd.read_csv("./datasets_IMDB-Movie-Data.csv")
'''
print(df.info())
print("*"*100)
print(df.head(1))
'''
#获取电影平均评分
print(df["Rating"].mean())
#获取导演人数
#print(len(set(df["Director"].tolist())))
print(len(df["Director"].unique()))
#获取演员人数
temp_actor_list = df["Actors"].str.split(",").tolist()
actors_list = [i for j in temp_actor_list for i in j]
actor_num = len(set(actors_list))
print(actor_num)