【稳住，can win】Pandas 数据合并和分组聚合

绘制电影分类统计条形图

from matplotlib import pyplot as plt
import pandas as pd
import numpy as np

file_path = "DataAnalysis/IMDB-Movie-Data.csv"
df = pd.read_csv(file_path)

# 统计分类列表
# 对索引得到的每条数据转换成字符串，再将字符串按“，”分割转换成一个列表，得到temp_list是一个二维列表
temp_list = df["Genre"].str.split(",").tolist() 
# 取二维列表中的每个列表进行去重，得到去重后的一维列表，列表内容为电影分类
genre_list = list(set([i for j in temp_list for i in j]))

# 构造为全0的数组
zero_df = pd.DataFrame(np.zeros((df.shape[0], len(genre_list))), columns=genre_list)

# 给每个电影出现的分类位置赋值1
for i in range(df.shape[0]):
    zero_df.loc[i, temp_list[i]] = 1

# 统计每个分类的电影的数量和
genre_count = zero_df.sum(axis=0)

# 排序
genre_count = genre_count.sort_values()
_x = genre_count.index
_y = genre_count.values

# 画图
plt.bar(range(len(_x)), _y)
plt.xticks(range(len(_x)), _x)
plt.show()

统计星巴克数量

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt

file_path = "DataAnalysis/starbucks_store_worldwide.csv"
df = pd.read_csv(file_path)
grouped = df.groupby("Country")

# 统计美国和中国星巴克数量
print(grouped["Brand"].count()["CN"])
print(grouped["Brand"].count()["US"])
# 统计中国每个省店铺的数量
china_data = df[df["Country"]=="CN"]
grouped = china_data.groupby("State/Province")["Brand"].count()

每个中国每个城市的店铺数量

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from matplotlib import font_manager

font = font_manager.FontProperties(fname="/usr/share/fonts/truetype/arphic-gbsn00lp/gbsn00lp.ttf")

file_path = "DataAnalysis/starbucks_store_worldwide.csv"

df = pd.read_csv(file_path)

df = df[df["Country"]=="CN"]
data1 = df.groupby(by="City")["Brand"].count().sort_values(ascending=False)[:50]
_x = data1.index
_y = data1.values

plt.bar(range(len(_x)), _y)
plt.xticks(range(len(_x)), _x, fontproperties=font, rotation=45)
plt.show()

统计不同年份书的数量

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from matplotlib import font_manager
from pandas.core import groupby

file_path = "DataAnalysis/books.csv"
df = pd.read_csv(file_path)
df = df[pd.notnull(df["original_publication_year"])]
grouped = df.groupby(by="original_publication_year")["title"].count()

统计不同年份书的平均评分情况

grouped = df["average_rating"].groupby(by=df["original_publication_year"]).mean()
_x = grouped.index
_y = grouped.values

plt.plot(range(len(_x)), _y)
plt.xticks(list(range(len(_x)))[::10], _x[::10].astype(int), rotation=45)
plt.show()