总结
分类统计
import pandas as pd
from matplotlib import pyplot as plt
import numpy as np
file_path = "./IMDB-Movie-Data.csv"
df = pd.read_csv(file_path)
print(df["Genre"].head(3))
#统计分类的列表
temp_list = df["Genre"].str.split(",").tolist() #[[],[],[]]
print(temp_list)
genre_list = list(set([i for j in temp_list for i in j]))#展开并且去除重复的值
print(genre_list)
#构造全为0的数组
zeros_df = pd.DataFrame(np.zeros((df.shape[0],len(genre_list))),columns=genre_list)#行数是为0表示1行,列数len()
# print(zeros_df)
#给每个电影出现分类的位置赋值1
# for i in range(df.shape[0]):
# #zeros_df.loc[0,["Sci-fi","Mucical"]] = 1
# zeros_df.loc[i,temp_list[i]] = 1
#
# # print(zeros_df.head(3))
#
# #统计每个分类的电影的数量和
# genre_count = zeros_df.sum(axis=0)
# print(genre_count)
#
# #排序
# genre_count = genre_count.sort_values()
# _x = genre_count.index
# _y = genre_count.values
# #画图
# plt.figure(figsize=(20,8),dpi=80)
# plt.bar(range(len(_x)),_y,width=0.4,color="orange")
# plt.xticks(range(len(_x)),_x)
# plt.show()
import pandas as pd
from matplotlib import font_manager
my_font = font_manager.FontProperties(fname="/Library/Fonts/Songti.ttc")
file_path = "./starbucks_store_worldwide.csv"
df = pd.read_csv(file_path)
df = df[df["Country"]=="CN"]
#使用matplotlib呈现出店铺总数排名前10的国家
#准备数据
data1 = df.groupby(by="City").count()["Brand"].sort_values(ascending=False)[:25]
_x = data1.index
_y = data1.values
#画图
plt.figure(figsize=(20,12),dpi=80)
# plt.bar(range(len(_x)),_y,width=0.3,color="orange")
plt.barh(range(len(_x)),_y,height=0.3,color="orange")
plt.yticks(range(len(_x)),_x,fontproperties=my_font)
plt.show()
分组
import pandas as pd
from matplotlib import pyplot as plt
file_path = "./books.csv"
df = pd.read_csv(file_path)
# print(df.head(2))
#
# print(df.info())
data1 = df[pd.notnull(df["original_publication_year"])]
#
grouped = data1.groupby(by="original_publication_year").count()["title"]
#不同年份书的平均评分情况
#去除original_publication_year列中nan的行
data1 = df[pd.notnull(df["original_publication_year"])]
grouped = data1["average_rating"].groupby(by=data1["original_publication_year"]).mean()
# print(grouped)
_x = grouped.index
_y = grouped.values
#画图
plt.figure(figsize=(20,8),dpi=80)
plt.plot(range(len(_x)),_y)
print(len(_x))
plt.xticks(list(range(len(_x)))[::10],_x[::10].astype(int),rotation=45)
plt.show()
数据合并join/merge
索引和复合索引