3.machinelearning的好伙伴plt

3.machinelearning的好伙伴plt

文件在下面提取：

链接：https://pan.baidu.com/s/1W3WzNMp_n4B39pcQhwP3SA
提取码：7b7r

折线图

import pandas as pd
import matplotlib.pyplot as plt


unrate = pd.read_csv('UNRATE.csv')
unrate['DATE'] = pd.to_datetime(unrate['DATE'])
print(unrate.head())

first_twelve = unrate[0:12]
#第一个参数是x轴的参数，第二个数值为y轴参数
plt.plot(first_twelve["DATE"],first_twelve['VALUE'])
plt.xticks(rotation = 0) # 对x轴的数值角度进行旋转
# 为x轴和y轴加上标签,设置字体大小
plt.xlabel('Month',fontsize = 15)
plt.ylabel('Unemployment Rate',fontsize = 15)
# 对图像设置题目
plt.title('Monthly Unemployment Rate')
plt.show()

直方图

import matplotlib.pyplot as plt
import  numpy as np

# 直方图

reviews = pd.read_csv('fandango_scores.csv')
cols = ["FILM","RT_user_norm","Metacritic_user_nom","IMDB_norm","Fandango_Ratingvalue","Fandango_Stars"]
nom_reviews = reviews[cols]

# 对每个数值进行个数的统计
fandango_distribution = nom_reviews['Fandango_Ratingvalue'].value_counts()
imdb_distribution = nom_reviews['IMDB_norm'].value_counts()
# 按照索引大小排序
fandango_distribution = fandango_distribution.sort_index()
imdb_distribution = imdb_distribution.sort_index()


fig, ax = plt.subplots()

# 绘制直方图
# ax.hist(nom_reviews['Fandango_Ratingvalue'],bins=20)  # 指定bins的个数
ax.hist(nom_reviews['Fandango_Ratingvalue'],range=(4,5),bins=20)  # 只统计4-5之间的
ax.set_ylim(0,50) # 设置y轴区间
ax.set_xlim(4.0,4.2) # 设置x轴区间
plt.show()

盒图

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

# 直方图

reviews = pd.read_csv('fandango_scores.csv')
cols = ["FILM","RT_user_norm","Metacritic_user_nom","IMDB_norm","Fandango_Ratingvalue","Fandango_Stars"]
nom_reviews = reviews[cols]

# 对每个数值进行个数的统计
fandango_distribution = nom_reviews['Fandango_Ratingvalue'].value_counts()
imdb_distribution = nom_reviews['IMDB_norm'].value_counts()
# 按照索引大小排序
fandango_distribution = fandango_distribution.sort_index()
imdb_distribution = imdb_distribution.sort_index()
print(fandango_distribution)
print(imdb_distribution)

fig, ax = plt.subplots()


# 绘制盒图
ax.boxplot(nom_reviews['RT_user_norm'])
ax.set_xticklabels('Rotten Tomatoes')
ax.set_ylim(0,5)
plt.show()

柱状图

import pandas as pd
import matplotlib.pyplot as plt
import numpy
"""
*********当对数据进行切片才能直接用date[]的形式，在定位莫一行只能用loc或者date[0:1]形式
"""
"""
用ax画图，fig控制实际的参数
"""

reviews = pd.read_csv('fandango_scores.csv')
cols = ["FILM","RT_user_norm","Metacritic_user_nom","IMDB_norm","Fandango_Ratingvalue","Fandango_Stars"]
nom_reviews = reviews[cols]
print(nom_reviews[0:1]) # 打印第一行数据
num_cols = ["RT_user_norm","Metacritic_user_nom","IMDB_norm","Fandango_Ratingvalue","Fandango_Stars"]
# 得到柱状图的数值
bar_values = nom_reviews.loc[0][num_cols]
print(bar_values)
# 得到柱状图的x轴坐标位置
ticks_position = range(1,6) # 定义坐标轴上每个位置
bar_position = numpy.arange(5) + 1

# 画图
fig ,ax = plt.subplots()    # 用ax画bar型图


# 竖直柱状图

ax.bar(bar_position,bar_values,0.5) # 第三个参数定义柱的宽度
ax.set_xticks(ticks_position)   # 设置坐标轴有多少位置
ax.set_xticklabels(num_cols,rotation = 50)  # 设定坐标轴标签
ax.set_xlabel('Name')
ax.set_ylabel('Values')
ax.set_title('first col values')

子图构建

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

# 引入数据
unrate = pd.read_csv("UNRATE.csv")
unrate['DATE'] = pd.to_datetime(unrate['DATE'])

# 创建子图布局

fig = plt.figure(figsize=(6,6)) # 创建图形,指定子图大小
ax1 = fig.add_subplot(4,3,1)  # 指定图像在四行三列图像的1号位置
ax2 = fig.add_subplot(4,3,2)
ax3 = fig.add_subplot(4,3,6)

ax1.plot(np.random.randint(1,5,5),np.arange(5))
ax2.plot(np.random.randint(1,5,5),np.arange(5))
ax3.plot(np.random.randint(1,5,5),np.arange(5))
plt.show()


# 将多条线条画在一个图上
# 画出多个线并对每个线段进行标识
unrate["MONTH"] = unrate["DATE"].dt.month # 得到每个月份对应的数据
unrate["MONTH"] = unrate["DATE"].dt.month
fig = plt.figure(figsize=(10,6))
color = ['red','blue','green','yellow','black']
for i in range(5):
    start = i*12
    end = (i+1)*12
    label = str(1948+i) # 添加标签
    plt.plot(unrate[start:end]["MONTH"],unrate[start:end]["VALUE"],c = color[i],label=label) # 但是不能显示
plt.legend(loc='best') # lengend解释说明，loc = 'best'，表示框的显示位置
plt.xlabel("MONTH")
plt.ylabel("RATE")

plt.show()

图像细节设置

import pandas as pd
import matplotlib.pyplot as plt

unrate = pd.read_csv("UNRATE.csv")
unrate["DATE"] = pd.to_datetime(unrate["DATE"])
unrate["MONTH"] = unrate['DATE'].dt.month

fig ,ax = plt.subplots()
ax.plot(unrate[0:12]['MONTH'],unrate[0:12]['VALUE'],c='red',label='first years')
ax.plot(unrate[12:24]['MONTH'],unrate[12:24]['VALUE'],c='blue',label='secend years')
# 去除边界
for key,spine in ax.spines.items():
    spine.set_visible(False)
# 去除坐标轴尺度
ax.tick_params(bottom = [],top = [], right = [], left = [])

ax.legend(loc = 'best')
plt.show()