pandas基础1

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.pyplot as mpl
import pandas as pd
mpl.rcParams['font.sans-serif'] = ['SimHei']
mpl.rcParams['axes.unicode_minus'] = False

#获取数据框
df = pd.read_csv("C:/Users/23608/Desktop/IMDB-Movie-Data.csv")
df.head()

	Rank	Title	Genre	Description	Director	Actors	Year	Runtime (Minutes)	Rating	Votes	Revenue (Millions)	Metascore
0	1	Guardians of the Galaxy	Action,Adventure,Sci-Fi	A group of intergalactic criminals are forced ...	James Gunn	Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...	2014	121	8.1	757074	333.13	76.0
1	2	Prometheus	Adventure,Mystery,Sci-Fi	Following clues to the origin of mankind, a te...	Ridley Scott	Noomi Rapace, Logan Marshall-Green, Michael Fa...	2012	124	7.0	485820	126.46	65.0
2	3	Split	Horror,Thriller	Three girls are kidnapped by a man with a diag...	M. Night Shyamalan	James McAvoy, Anya Taylor-Joy, Haley Lu Richar...	2016	117	7.3	157606	138.12	62.0
3	4	Sing	Animation,Comedy,Family	In a city of humanoid animals, a hustling thea...	Christophe Lourdelet	Matthew McConaughey,Reese Witherspoon, Seth Ma...	2016	108	7.2	60545	270.32	59.0
4	5	Suicide Squad	Action,Adventure,Fantasy	A secret government agency recruits some of th...	David Ayer	Will Smith, Jared Leto, Margot Robbie, Viola D...	2016	123	6.2	393727	325.02	40.0

#将评分一栏单独提取出来
cinema = df["Rating"]
cinema

0      8.1
1      7.0
2      7.3
3      7.2
4      6.2
      ... 
995    6.2
996    5.5
997    6.2
998    5.6
999    5.3
Name: Rating, Length: 1000, dtype: float64

#转化为numpy格式
movies = np.array(cinema)
#将数组内的结果求和除以数组的shape得到平均值
result = sum(movies) / movies.shape[0]
result = round(result,2)
result

tx1 = df["Rating"]
tx2 = df["Runtime (Minutes)"]
print("Rating",tx1.head())
print("Runtime (Minutes)",tx2.head())

plt.subplots(1, 1,figsize=(10,8), dpi=100)
plt.scatter(y, tx1,label='Rating')
plt.title('Rating分布')
plt.legend()
 
plt.subplots(1, 1,figsize=(10,8), dpi=100)
plt.scatter(y,tx2,label='Runtime (Minutes)')
plt.title('Runtime (Minutes)分布')
plt.legend()
plt.show()

tx3 = df["Genre"]
tx4 = tx3.iloc[2].split(",")
temp = []
for i in range(tx3.shape[0]):
    tx4 = np.array(tx3.iloc[i].split(","))
    for j in range(tx4.shape[0]):
        temp.append(tx4[j])
temp
result = np.array(temp)
print(result.shape[0])
result[:5]

df2 = pd.DataFrame({"key":result， })
df2.merge(df2)

df3 = df2.groupby(["key"]).size()
df3

x_axis = df3.index
y_axis = df3.values

x_axis

y_axis

plt.subplots(1, 1,figsize=(10,8), dpi=100)
plt.pie(y_axis,labels=x_axis)
plt.title('不同类别的电影数量')
plt.legend()