机器学习之路--Matplotlib

1.绘制折线图

在pandas里面有一种数据类型为datatime ，可以将不规范的日期改为：xxxx-xx-xx

import pandas as pd
import numpy as np
a = pd.read_csv('UNRATE.csv')
a['DATE'] = pd.to_datetime(a['DATE'])
print(a.head(12))

折线图

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
a = pd.read_csv('UNRATE.csv')
b = a[0:12]
plt.plot(b['DATE'],b['VALUE'])
plt.show()

这样就能绘制出一个折线图了

如果横坐标写不下怎么办？我们可以将文字竖着写或者指定一个角度

plt.xticks(rotation = 45)   #其中的45表示45°（和数学里面一样）

一般情况下要写横坐标与纵坐标要表达什么，还有标题

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
a = pd.read_csv('UNRATE.csv')     #导入文件
b = a[0:12]      #将数据的前12条提取出来
plt.plot(b['DATE'],b['VALUE'])      #导入横纵坐标的数据
plt.xticks(rotation = 90)     #横坐标90
plt.xlabel('Month')              #横坐标名称
plt.ylabel('Unemployment Rate')      #纵坐标名称
plt.title('Monthly Unemployment Trends, 1948')      #标题
plt.show()       #展示

输出;

unrate['MONTH'] = unrate['DATE'].dt.month
unrate['MONTH'] = unrate['DATE'].dt.month
fig = plt.figure(figsize=(6,3))          #图的大小

plt.plot(unrate[0:12]['MONTH'], unrate[0:12]['VALUE'], c='red')          #c为颜色
plt.plot(unrate[12:24]['MONTH'], unrate[12:24]['VALUE'], c='blue')
   #在同一张图上绘制两条折线并进行对比
plt.show()

fig = plt.figure(figsize=(10,6))
colors = ['red', 'blue', 'green', 'orange', 'black']
for i in range(5):
    start_index = i*12
    end_index = (i+1)*12
    subset = unrate[start_index:end_index]
    plt.plot(subset['MONTH'], subset['VALUE'], c=colors[i])
    #绘制5条折线在一张图中，用颜色加以区分
plt.show()

fig = plt.figure(figsize=(10,6))
colors = ['red', 'blue', 'green', 'orange', 'black']
for i in range(5):
    start_index = i*12
    end_index = (i+1)*12
    subset = unrate[start_index:end_index]
    label = str(1948 + i)
    plt.plot(subset['MONTH'], subset['VALUE'], c=colors[i], label=label)
plt.legend(loc='best')      #legend表示添加图例，loc是图例在折线图中的位置，best表示在系统觉得合适的位置，当然也可以自定义位置，位置的选择请help（legend）
#print help(plt.legend)
plt.show()

输出：

最终版：

fig = plt.figure(figsize=(10,6))
colors = ['red', 'blue', 'green', 'orange', 'black']
for i in range(5):
    start_index = i*12
    end_index = (i+1)*12
    subset = unrate[start_index:end_index]     #数据区间
    label = str(1948 + i)       #图例每次写的折线标题
    plt.plot(subset['MONTH'], subset['VALUE'], c=colors[i], label=label)
plt.legend(loc='upper left')       #放到左上角
plt.xlabel('Month, Integer')       #横坐标标题
plt.ylabel('Unemployment Rate, Percent')   #纵坐标标题
plt.title('Monthly Unemployment Trends, 1948-1952')      #折线图标题

plt.show()

输出：

3、条形图与散点图

import pandas as pd
import numpy as np
from numpy import arange
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]
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']

bar_heights = norm_reviews.ix[0, num_cols].values     #当前柱的高度
#print bar_heights
bar_positions = arange(5) + 0.75     #0.75是第一个柱离原点的距离    然后每个柱距离为1 一共5个柱
#print bar_positions
fig, ax = plt.subplots()
ax.bar(bar_positions, bar_heights, 0.5)      #0.5表示柱子的宽度
plt.show()

num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_heights = norm_reviews.ix[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')     #横坐标
ax.set_ylabel('Average Rating')     #纵坐标
ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)')   #标题
plt.show()

输出：

当然，也可以将柱形图变为横着的

import matplotlib.pyplot as plt
from numpy import arange
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']

bar_widths = norm_reviews.ix[0, num_cols].values
bar_positions = arange(5) + 0.75
tick_positions = range(1,6)
fig, ax = plt.subplots()
ax.barh(bar_positions, bar_widths, 0.5)     #需要改变的地方，将bar改为barh

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.show()

输出：

散点图：

fig, ax = plt.subplots()
ax.scatter(norm_reviews['Fandango_Ratingvalue'], norm_reviews    #scatter画散点图
['RT_user_norm'])
ax.set_xlabel('Fandango')
ax.set_ylabel('Rotten Tomatoes')
plt.show()

输出：

画两个散点图：

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()

输出：

用fig设置参数，ax做实际画图的操作

4、柱形图与盒图

求数据的频数，并可视化

import pandas as pd
import numpy as np
from numpy import arange
import matplotlib.pyplot as plt
reviews = pd.read_csv('fandango_scores.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']
norm_reviews = reviews[cols]
print(norm_reviews[:5])      #输出数据
fandango_distribution = norm_reviews['Fandango_Ratingvalue'].value_counts()       #需要数据
fandango_distribution = fandango_distribution.sort_index()     #从小到大排序

imdb_distribution = norm_reviews['IMDB_norm'].value_counts()
imdb_distribution = imdb_distribution.sort_index()

print(fandango_distribution)    #一组数据的频数，比如4.3出现了6次 表示为：4.3     6
print(imdb_distribution)        #另一组数据的频数
fig, ax = plt.subplots()
ax.hist(norm_reviews['Fandango_Ratingvalue'])       #画出柱形图
#ax.hist(norm_reviews['Fandango_Ratingvalue'],bins=20)     #bins = 20 表示一共有20个柱子
#ax.hist(norm_reviews['Fandango_Ratingvalue'], range=(4, 5),bins=20)     #range代表了横坐标的区间
plt.show()

import pandas as pd
import numpy as np
from numpy import arange
import matplotlib.pyplot as plt
reviews = pd.read_csv('fandango_scores.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']
norm_reviews = reviews[cols]

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)    #指定了这组数据的y轴取值区间

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()

输出：（在ml里run一下，太长了）

盒图（四分图，找中位数）：

import pandas as pd
import numpy as np
from numpy import arange
import matplotlib.pyplot as plt
reviews = pd.read_csv('fandango_scores.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']
norm_reviews = reviews[cols]
fig, ax = plt.subplots()
ax.boxplot(norm_reviews['RT_user_norm'])
ax.set_xticklabels(['Rotten Tomatoes'])
ax.set_ylim(0, 5)
plt.show()

输出：

这样，就可以清晰的看到中位数的位置以及大致的数据区间

也可以在一张图上放入多张盒图，这样就可以区分各个属性的特征了

import pandas as pd
import numpy as np
from numpy import arange
import matplotlib.pyplot as plt
reviews = pd.read_csv('fandango_scores.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']
norm_reviews = reviews[cols]
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()

输出：

5、闲的蛋疼系列：

可以将坐标轴去掉：

for key,spine in ax.spines.items():
    spine.set_visible(False)     #去掉横纵坐标轴的线

可以去掉坐标轴的锯齿：

ax.tick_params(bottom="off", top="off", left="off", right="off")

6、最后的一些方法

*****一般在做图时为了让图中表达的清晰，让图尽量在一行或两行

fig = plt.figure(figsize=(12, 12))   #figsize参数调试

在作图时的颜色可以用自己定义的颜色

#Color
import pandas as pd
import matplotlib.pyplot as plt

women_degrees = pd.read_csv('percent-bachelors-degrees-women-usa.csv')
major_cats = ['Biology', 'Computer Science', 'Engineering', 'Math and Statistics']

cb_dark_blue = (0/255, 107/255, 164/255)    #自定义颜色，注意格式
cb_orange = (255/255, 128/255, 14/255)

fig = plt.figure(figsize=(12, 12))

for sp in range(0,4):
    ax = fig.add_subplot(2,2,sp+1)
    # The color for each line is assigned here.
    ax.plot(women_degrees['Year'], women_degrees[major_cats[sp]], c=cb_dark_blue, label='Women')
    ax.plot(women_degrees['Year'], 100-women_degrees[major_cats[sp]], c=cb_orange, label='Men')
    for key,spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0,100)
    ax.set_title(major_cats[sp])
    ax.tick_params(bottom="off", top="off", left="off", right="off")

plt.legend(loc='upper right')
plt.show()

如果要让线的宽度改变，让

ax.plot(women_degrees['Year'], women_degrees[major_cats[sp]], c=cb_dark_blue, label='Women', linewidth=10)   #linewidth是改变线宽度的参数
    ax.plot(women_degrees['Year'], 100-women_degrees[major_cats[sp]], c=cb_orange, label='Men', linewidth=10)

最终附上一波此例完整版：（其中有在图中某一坐标上标出此点名称）：

import pandas as pd
import numpy as np
from numpy import arange
import matplotlib.pyplot as plt
women_degrees = pd.read_csv('percent-bachelors-degrees-women-usa.csv')
major_cats = ['Biology', 'Computer Science', 'Engineering', 'Math and Statistics']
stem_cats = ['Engineering', 'Computer Science', 'Psychology', 'Biology', 'Physical Sciences', 'Math and Statistics']
cb_dark_blue = (0/255, 107/255, 164/255)
cb_orange = (255/255, 128/255, 14/255)
fig = plt.figure(figsize=(18, 3))

for sp in range(0, 6):
    ax = fig.add_subplot(1, 6, sp + 1)
    ax.plot(women_degrees['Year'], women_degrees[stem_cats[sp]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100 - women_degrees[stem_cats[sp]], c=cb_orange, label='Men', linewidth=3)
    for key, spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0, 100)
    ax.set_title(stem_cats[sp])
    ax.tick_params(bottom="off", top="off", left="off", right="off")
plt.legend(loc='upper right')
plt.show()
fig = plt.figure(figsize=(18, 3))

for sp in range(0, 6):
    ax = fig.add_subplot(1, 6, sp + 1)
    ax.plot(women_degrees['Year'], women_degrees[stem_cats[sp]], c=cb_dark_blue, label='Women', linewidth=3)
    ax.plot(women_degrees['Year'], 100 - women_degrees[stem_cats[sp]], c=cb_orange, label='Men', linewidth=3)
    for key, spine in ax.spines.items():
        spine.set_visible(False)
    ax.set_xlim(1968, 2011)
    ax.set_ylim(0, 100)
    ax.set_title(stem_cats[sp])
    ax.tick_params(bottom="off", top="off", left="off", right="off")

    if sp == 0:            #设置if语句后会对需要的图上加点的名称
        ax.text(2005, 87, 'Men')    #在坐标（2005，87）处标men
        ax.text(2002, 8, 'Women')
    elif sp == 5:
        ax.text(2005, 62, 'Men')
        ax.text(2001, 35, 'Women')
plt.show()

输出：