机器学习初入门03 - Matplotlib

这一部分很简单，所以以代码的形式给出，在实际学习开发中，Matplotlib最好只把它当成一个画图的工具来用，没有必要深究其实现原理是什么。

一、折线图的绘制

import pandas as pd

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

print(unrate.head(5))

#pandas应该会自动把xxxx/xx/xx转化为标准时间格式xxxx-xx-xx，如果没有，用下面一行代码实现

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

原始数据：                    代码执行结果：

import matplotlib.pyplot as plt

#画图

plt.plot()

#把画的图显示出来

plt.show()

first_twelve = unrate[0:12]

#第一个参数为横轴，第二个参数为纵轴

plt.plot(first_twelve["DATE"], first_twelve["VALUE"])

plt.show()

#可以看到上图的横坐标丑的一匹，怎么办呢

plt.plot(first_twelve["DATE"], first_twelve["VALUE"])

#指定x轴标签的角度

plt.xticks(rotation=45)

plt.show()

#给图像加标签

plt.plot(first_twelve["DATE"], first_twelve["VALUE"])

plt.xticks(rotation=45)

plt.xlabel("DATA")

plt.ylabel('Unemployment Rate')

plt.title('Monthly unemployment Trends, 1948')

plt.show()

二、子图操作

import matplotlib.pyplot as plt

#定义画图区域

fig = plt.figure()

#画子图

#前两个参数代表是一个2*2的画图区域，最后一个参数表示该子图的位置

ax1 = fig.add_subplot(2,2,1)

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

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

plt.show()

import numpy as np

#指定画图区域的大小

fig = plt.figure(figsize = (3,3))

ax1 = fig.add_subplot(2,1,1)

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

ax1.plot(np.random.randint(1,5,5), np.arange(5))

ax2.plot(np.arange(10)*3, np.arange(10))

plt.show()

import pandas as pd

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

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

unrate['MONTH'] = unrate['DATE'].dt.month

fig = plt.figure(figsize=(6,3))

#在一个图里画多条折线，c指定颜色，可以直接是颜色名称，也可以是RGB值

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

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

plt.show()

fig = plt.figure(figsize=(10, 6))

colors = ['red', 'blue', 'green', 'orange', 'black']

for i in range(5):

subset = unrate[start_index:end_index]

label = str(1948 + i)

plt.plot(subset['MONTH'], subset["VALUE"], c=colors[i], label=label)

#标签框出现在哪

plt.legend(loc='best')

plt.show()

三、条形图与散点图

import pandas as pd

reviews = pd.read_csv('fandango_scores.csv')

cols = [

'FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm',

'Fandango_Ratingvalue', 'Fandango_Stars'

]

norm_reviews = reviews[cols]

print(norm_reviews[:1] , '\n')

import matplotlib.pyplot as plt

from numpy import arange

num_cols = [

'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue',

'Fandango_Stars'

]

#定义条形图的条高

框也一样。

框是指定column，但是在python3中ix是不赞成使用的

# bar_heights = norm_reviews.ix[0,num_cols].values

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

print(norm_reviews.loc[0][num_cols], '\n\n', bar_heights, '\n')

#定义条的位置，即离原点有多远

bar_positions = arange(5) + 0.75

print(bar_positions)

ax = plt.subplot()

#画条形图，第三个参数定义条宽

ax.bar(bar_positions, bar_heights, 0.3)

plt.show()

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

#python range() 函数可创建一个整数列表

tick_positions = range(1, 6)

ax = plt.subplot()

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)')

#如果图片显示不全，用下面的命令

plt.tight_layout()

plt.show()

bar_widths = norm_reviews.loc[0][num_cols].values

tick_positions = range(1, 6)

ax = plt.subplot()

ax.barh(bar_positions, bar_widths, 0.5)

ax.set_yticks(tick_positions)

ax.set_yticklabels(num_cols)

ax.set_ylabel('Rating Source')

ax.set_xlabel('Average Rating')

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

plt.tight_layout()

plt.show()

#画散点图

ax = plt.subplot()

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

ax.set_xlabel('Fandango')

ax.set_ylabel('Rotten Tomatoes')

plt.show()

fig = plt.figure(figsize=(5, 10))

ax1 = fig.add_subplot(2, 1, 1)

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

ax1.scatter(norm_reviews['Fandango_Ratingvalue'], norm_reviews['RT_user_norm'])

ax1.set_xlabel('Fandango')

ax1.set_ylabel('Rotten Tomatoes')

ax2.scatter(norm_reviews['RT_user_norm'], norm_reviews['Fandango_Ratingvalue'])

ax2.set_xlabel('Rotten Tomatoes')

ax2.set_ylabel('Fandango')

plt.show()

四、柱形图与盒图

import pandas as pd

import matplotlib.pyplot as plt

reviews = pd.read_csv('fandango_scores.csv')

cols = [

'FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm',

'Fandango_Ratingvalue', 'Fandango_Stars'

]

norm_reviews = reviews[cols]

# print(norm_reviews[:5])

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()

ax = plt.subplot()

个

ax.hist(norm_reviews['Fandango_Ratingvalue'])

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

# range指定显示在图上的总区间

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

plt.show()

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

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

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

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

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

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

ax1.set_title('Distribution of Fandango Ratings')

#指定y轴区间

ax1.set_ylim(0, 50)

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

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

ax2.set_ylim(0, 50)

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

ax3.set_title('Distribution of Metacritic Ratings')

ax3.set_ylim(0, 50)

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

ax4.set_title('Distribution of IMDB Ratings')

ax4.set_ylim(0, 50)

plt.show()

#画盒图

ax = plt.subplot()

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.tight_layout()

plt.show()