pandas之常用统计及字符串离散化

统计方法

print("*"*25+"直方图"+"*"*25)

*************************直方图*************************

import pandas as pd

file_path="./IMDB-Movie-Data.csv"

df = pd.read_csv(file_path)

print(df.head(1))
print(df.info())

   Rank                    Title                    Genre  \
0     1  Guardians of the Galaxy  Action,Adventure,Sci-Fi   

                                         Description    Director  \
0  A group of intergalactic criminals are forced ...  James Gunn   

                                              Actors  Year  Runtime (Minutes)  \
0  Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...  2014                121   

   Rating   Votes  Revenue (Millions)  Metascore  
0     8.1  757074              333.13       76.0  
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 entries, 0 to 999
Data columns (total 12 columns):
 #   Column              Non-Null Count  Dtype  
---  ------              --------------  -----  
 0   Rank                1000 non-null   int64  
 1   Title               1000 non-null   object 
 2   Genre               1000 non-null   object 
 3   Description         1000 non-null   object 
 4   Director            1000 non-null   object 
 5   Actors              1000 non-null   object 
 6   Year                1000 non-null   int64  
 7   Runtime (Minutes)   1000 non-null   int64  
 8   Rating              1000 non-null   float64
 9   Votes               1000 non-null   int64  
 10  Revenue (Millions)  872 non-null    float64
 11  Metascore           936 non-null    float64
dtypes: float64(3), int64(4), object(5)
memory usage: 93.9+ KB
None

#rating,runtime分布情况-直方图

runtime_data=df["Runtime (Minutes)"].values #ndarray类型
max_runtime=runtime_data.max()
min_runtime=runtime_data.min()

from matplotlib import pyplot as plt
num_bin = (max_runtime-min_runtime)//5 #设置组距


plt.figure(figsize=(20,8),dpi=80) #设置图形大小
plt.hist(runtime_data,num_bin)
# print(max_runtime-min_runtime)

plt.xticks(range(min_runtime,max_runtime+5,5))#设置x轴

plt.show()

runtime_data=df["Rating"].values 
max_runtime=runtime_data.max()
min_runtime=runtime_data.min()

num_bin_list=[1.9,3.5]
i=3.5
while i<=max_runtime:
    i += 0.5
    num_bin_list.append(i)
    
# num_bin_list = [0.5]*13+[0.6]
print(num_bin_list)


plt.figure(figsize=(20,8),dpi=80) 
plt.hist(runtime_data,num_bin_list)

# _x = [min_runtime]
# i=min_runtime
# while i<=max_runtime+0.5:
#   i=i+0.5
#   _x.append(i)
    
plt.xticks(num_bin_list)
plt.show()

[1.9, 3.5, 4.0, 4.5, 5.0, 5.5, 6.0, 6.5, 7.0, 7.5, 8.0, 8.5, 9.0, 9.5]

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 entries, 0 to 999
Data columns (total 12 columns):
 #   Column              Non-Null Count  Dtype  
---  ------              --------------  -----  
 0   Rank                1000 non-null   int64  
 1   Title               1000 non-null   object 
 2   Genre               1000 non-null   object 
 3   Description         1000 non-null   object 
 4   Director            1000 non-null   object 
 5   Actors              1000 non-null   object 
 6   Year                1000 non-null   int64  
 7   Runtime (Minutes)   1000 non-null   int64  
 8   Rating              1000 non-null   float64
 9   Votes               1000 non-null   int64  
 10  Revenue (Millions)  872 non-null    float64
 11  Metascore           936 non-null    float64
dtypes: float64(3), int64(4), object(5)
memory usage: 93.9+ KB
None

print("*"*25+"常用方法"+"*"*25)

print("平均分:%f"%df["Rating"].mean())
print("导演人数:%d"%len(set(df["Director"].tolist())))
print("导演人数unique:%d"%len(df["Director"].unique()))
actors_list=df["Actors"].str.split(",").tolist()
actors_list=[i for j in actors_list for i in j]
# import numpy as np
# actors_list=list(np.array(actors_list).flatten())
actors_num=len(set(actors_list))
print("演员人数:%d"%actors_num)
#最大值max(),最小值min(),平均值mean(),最大值位置argmax(),最小值位置argmin(),中位数median()

平均分:6.723200
导演人数:644
导演人数unique:644
演员人数:2394

字符串离散化