python matlib库_Python3_matpltlib可视化库操作

import pandas as pd

unrate = pd.read_csv("UNRATE.csv")

unrate["DATE"]=pd.to_datetime(unrate["DATE"])

#to_datetime 转换为当前的日期格式

unrate.head()

DATE为日期，VALUE为当年当月的失业人数占总人数的百分比

绘制折线图import matplotlib.pyplot as plt 导入matplotlib库

plt.plot() plot(要绘制的数据)

plt.show() 显示折线图

plt.plot(unrate["DATE"].head(12),unrate["VALUE"].head(12))

plt.show()

plt.plot(unrate["DATE"].head(12),unrate["VALUE"].head(12))

plt.xticks(rotation=45)#调整横坐标的值的角度为45度

plt.show()

plt.plot(unrate["DATE"].head(12),unrate["VALUE"].head(12))

plt.xlabel("Month") #给x，Y轴添加名称

plt.ylabel("Unemployment Rate")

plt.title("Monthly Unemployment Trends,1948") #给折线图命名

plt.show()

子图的操作import matplotlib.pyplot as plt

fig = plt.figure() #指定作图域

ax1 = fig.add_subplot(2,2,1) #添加一个2行2列的在第一个位置的子图

ax2 = fig.add_subplot(2,2,2)

ax3 = fig.add_subplot(2,2,4)

plt.show()

import matplotlib.pyplot as plt

fig = plt.figure()

plt.plot(unrate[0:12]["DATE"],unrate[0:12]["VALUE"],c="red")

plt.plot(unrate[12:24]["DATE"],unrate[12:24]["VALUE"],c="blue")

plt.show()

import matplotlib.pyplot as plt

fig = plt.figure()

colors = ['red', 'blue', 'green', 'orange', 'black']for i in range(5):

start_index = i*12

end_index = (i+1)*12

plt.plot(unrate[start_index:end_index]['DATE'], unrate[start_index:end_index]['VALUE'], c=colors[i])

plt.show()

import matplotlib.pyplot as plt

fig = plt.figure()

colors = ['red', 'blue', 'green', 'orange', 'black']for i in range(5):

start_index = i*12

end_index = (i+1)*12

label = str(1948 + i)

plt.plot(unrate[start_index:end_index]['DATE'], unrate[start_index:end_index]['VALUE'], c=colors[i],label=label)

plt.legend(loc='best')

plt.xlabel("Year")

plt.ylabel("Rate")

plt.title("Year Rate,1948-1952")

plt.show()

3条形图与散点图import pandas as pd #导入pandas库

reviews = pd.read_csv("fandango_score_comparison.csv") #导入fandango_score_comparison.csv数据

cols=['FILM','RT_user_norm','Metacritic_user_nom','IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars'] #创建cols列表

norm_reviews=reviews[cols] #取出表中的cols列

norm_reviews.head()

import matplotlib.pyplot as plt

from numpy import arange

num_cols=['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']#获取的列中数据即分别对应条形图的高度

bar_heights = norm_reviews.loc[0,num_cols].values

#print(bar_heights)#[4.3 3.55 3.9 4.5 5.0]bar_positions=arange(5)+0.75

#print(bar_positions)#[0.75 1.75 2.75 3.75 4.75]fig, ax = plt.subplots()

ax.bar(bar_positions,bar_heights,0.5)

plt.show()

bar()方法有两个必需的参数，左边和高度。

我们使用左参数来指定条形图左侧的x坐标。

我们使用高度参数来指定每个栏的高度

fig,ax = plt.subplots()等价于：

fig = plt.figure()

ax = fig.add_subplot(1,1,1)

#柱形图横着画

ax.bar(bar_positions,bar_heights,0.5)

#柱形图竖着画

#ax.barh(bar_positions,bar_heights,0.5)

num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']bar_heights=norm_reviews.loc[0,num_cols].values

bar_positions = arange(5)+0.75

tick_positions=range(1,6)

fig, ax = plt.subplots()

ax.bar(bar_positions,bar_heights,0.5)

ax.set_xticks(tick_positions)

ax.set_xticklabels(num_cols,rotation=45)

ax.set_xlabel("Rating Source")

ax.set_ylabel("Average Rating")

ax.set_title("Average User Rating For Avengers: Age of Ultron (2015)")

plt.show()

fig,ax=plt.subplots()

ax.scatter(norm_reviews['Fandango_Ratingvalue'], norm_reviews['RT_user_norm'])

ax.set_xlabel("Fandango")

ax.set_ylabel("Rotten")

plt.show()

import pandas as pd

import matplotlib.pyplot as plt

reviews=pd.read_csv("fandango_score_comparison.csv")

cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']norm_reviews=reviews[cols]norm_reviews

fandango_distribution=norm_reviews["Fandango_Ratingvalue"].value_counts()

fandango_distribution=fandango_distribution.sort_index()

imdb_distribution=norm_reviews["IMDB_norm"].value_counts()

imdb_distribution=imdb_distribution.sort_index()

print(fandango_distribution)

print(imdb_distribution)

fig,ax=plt.subplots()

#ax.hist(norm_reviews["Fandango_Ratingvalue"])

#ax.hist(norm_reviews["Fandango_Ratingvalue"],bins=20)

ax.hist(norm_reviews["Fandango_Ratingvalue"],range=(4,5),bins=20)

plt.show()

fig=plt.figure(figsize=(5,20))

ax1=fig.add_subplot(4,1,1)

ax2=fig.add_subplot(4,1,2)

ax3=fig.add_subplot(4,1,3)

ax4=fig.add_subplot(4,1,4)

ax1.hist(norm_reviews["Fandango_Ratingvalue"],bins=20,range=(0,5))

ax1.set_title("Distribution of Fandango Ratings")

ax1.set_ylim(0,50)

ax2.hist(norm_reviews["RT_user_norm"],bins=20,range=(0,5))

ax2.set_title("Distribution of Rotten Tomatoes Ratings")

ax2.set_ylim(0,50)

ax3.hist(norm_reviews["Metacritic_user_nom"],bins=20,range=(0,5))

ax3.set_title("Distribution of M Ratings")

ax3.set_ylim(0,50)

ax4.hist(norm_reviews["IMDB_norm"],bins=20,range=(0,5))

ax4.set_title("Distribution of IMB Ratings")

ax4.set_ylim(0,50)

plt.show()

fig,ax=plt.subplots()

ax.boxplot(norm_reviews["RT_user_norm"])

ax.set_xticklabels(["Rotten Tomatoes"])

ax.set_ylim(0,5)

plt.show()

num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']fig,ax=plt.subplots()

ax.boxplot(norm_reviews[num_cols].values)

ax.set_xticklabels(num_cols,rotation=90)

ax.set_ylim(0,5)

plt.show()

作者：龙神~