Matplotlib模块

Matplotlib模块是Python中用来画图的模块

制作折线图
利用plt.plot(x轴,y轴)结构创建折线图

import matplotlib.pyplot as plt
import pandas as pd

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

data["DATE"] = pd.to_datetime(data["DATE"])#利用pd.to_datetime()函数，可以将非标准型时间数据转换成标准型时间数据
print(data.head(3))

# plt.plot() #利用plot()函数画图
# plt.show() #show()函数展示图像

first_twive = data[0:12]
plt.plot(first_twive["DATE"], first_twive["VALUE"])#指定x轴和y轴内容，可以利用linewidth参数设定折线宽度

plt.xticks(rotation = 45)#将x轴的label旋转45度

plt.xlabel("Month")#指定label
plt.ylabel("Unemployment Rate")
plt.title("Monthly Unemployment Rate")

plt.show()

画两条线在同一图中

import matplotlib.pyplot as plt
import pandas as pd

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

fig = plt.figure(figsize=(6, 3))#figure()函数用来指定图像对象，figsize参数指定图的长与宽

plt.plot(data["DATE"][0:12], data["VALUE"][0:12], c="red")
plt.plot(data["DATE"][12:24], data["VALUE"][12:24], c="blue")#利用两个plt.plot()函数可以在同一张图上画出两条线，c参数控制颜色
plt.xticks(rotation=45)

fig.show()

加入lengend

import matplotlib.pyplot as plt
import pandas as pd

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

data["DATE"] = pd.to_datetime(data["DATE"])
data["Month"] = data["DATE"].dt.month#利用dt.month函数将标准时间中的月份提取出来

colors = ["red", "blue", "green", "orange", "black"]
for i in range(5):
    start_index = i * 12
    end_index = (i + 1) * 12
    subset = data[start_index:end_index]
    label = str(1948 + i)
    plt.plot(subset["Month"], subset["VALUE"], c=colors[i], label=label)#在曲线函数中指定label后还需要对整个图做操作才能显示legend
    
plt.legend(loc="best")#loc参数控制legend位置，best的意思是让plt选择最佳位置

plt.show()

---

制作子图

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

fig = plt.figure()#figure()函数用来指定画图域，可以指定参数来确定图长与图宽

ax1 = fig.add_subplot(2, 2, 1)#制作两行两列图中的第一张图
ax2 = fig.add_subplot(2, 2, 2)#制作两行两列图中的第二张图
ax3 = fig.add_subplot(2, 2, 4)#制作两行两列图中的第四张图

ax1.plot(data["DATE"][0:12], data["VALUE"][0:12])
ax2.plot(data["DATE"][12:24], data["VALUE"][12:24])
ax3.plot(data["DATE"][24:36], data["VALUE"][24:36])

plt.show()#因为没有制作第三张图，所以没有左下角的图

import matplotlib.pyplot as plt
import numpy as np

fig = plt.figure(figsize=(3, 6))#利用figsize函数指定了图长和图宽

ax1 = fig.add_subplot(2, 1, 1)
ax2 = fig.add_subplot(2, 2, 2)

ax1.plot(np.random.randint(1, 5, 5), range(1, 6))
ax2.plot(np.arange(10) * 3, np.arange(10))

plt.show()

---

制作条形图

import pandas as pd
import matplotlib.pyplot as plt
from numpy import arange

data = pd.read_csv("fandango_scores.csv")

cols = ["FILM", "RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue", "Fandango_Stars"]
data_norm = data[cols]
num_cols = ["RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue", "Fandango_Stars"]

bar_height = data_norm.loc[0, num_cols].values

bar_positions = arange(5) + 0.75#表示距远点距离
tick_positions = [0.5, 1.5, 2.5, 3.5, 4.5]

fig, ax = plt.subplots()#fig一般用来控制图像对象子，ax用来具体生成子图

ax.bar(bar_positions, bar_height, 0.3))#bar()函数两个参数，第一个参数为柱状图位置参数，第二个参数为柱状图高度，第三个参数为柱宽

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("Rating")

plt.show()

横着制作柱状图

import pandas as pd
import matplotlib.pyplot as plt
from numpy import arange

data = pd.read_csv("fandango_scores.csv")

cols = ["FILM", "RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue", "Fandango_Stars"]
data_norm = data[cols]
num_cols = ["RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue", "Fandango_Stars"]

bar_height = data_norm.loc[0, num_cols].values

bar_positions = arange(5) + 0.75
tick_positions = [0.5, 1.5, 2.5, 3.5, 4.5]

fig, ax = plt.subplots()

ax.barh(bar_positions, bar_height, 0.5)#barh()函数可以横着生成柱状图

ax.set_yticks(tick_positions)
ax.set_yticklabels(num_cols)

ax.set_ylabel("Rating Source")
ax.set_xlabel("Average Rating")
ax.set_title("Rating")

plt.show()

---

制作散点图

import pandas as pd
import matplotlib.pyplot as plt

data = pd.read_csv("fandango_scores.csv")

cols = ["FILM", "RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue", "Fandango_Stars"]
data_norm = data[cols]

fig, ax = plt.subplots()

ax.scatter(data_norm["Fandango_Ratingvalue"], data_norm["RT_user_norm"])#利用scatter()函数，第一个参数为x轴内容，第二个参数为y轴内容

ax.set_xlabel("Fandango")
ax.set_ylabel("Rotten Tomatoes")

plt.show()

增加子图，复杂版

import pandas as pd
import matplotlib.pyplot as plt

data = pd.read_csv("fandango_scores.csv")

cols = ["FILM", "RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue", "Fandango_Stars"]
data_norm = data[cols]

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

ax1 = fig.add_subplot(2, 1, 1)
ax2 = fig.add_subplot(2, 1, 2)

ax1.scatter(data_norm["Fandango_Ratingvalue"], data_norm["RT_user_norm"])
ax1.set_xlabel("Fandango")
ax1.set_ylabel("Rotten Tomatoes")

ax2.scatter(data_norm["RT_user_norm"], data_norm["Fandango_Ratingvalue"])
ax2.set_xlabel("Rotten Tomatoer")
ax2.set_ylabel("Fandango")

plt.show()

---

制作分布图

import pandas as pd
import matplotlib.pyplot as plt

data = pd.read_csv("fandango_scores.csv")

cols = ["FILM", "RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue", "Fandango_Stars"]
data_norm = data[cols]

fandango_distribution = data_norm["Fandango_Ratingvalue"].value_counts()#value_counts()函数可以用来统计每个值有多少个样本
fandango_distribution = fandango_distribution.sort_index()#在sort_index()函数后数据会按照大小排列

print(fandango_distribution.head(3))

fig, ax = plt.subplots()

ax.hist(data_norm["Fandango_Ratingvalue"], bins=30)#利用hist()函数可以画出柱状图，bins参数用来指定间隔，可以使用range=(4,5)参数表示只显示4到5之间的数据分布

plt.show()

加子图复杂版

import pandas as pd
import matplotlib.pyplot as plt

data = pd.read_csv("fandango_scores.csv")

cols = ["FILM", "RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue", "Fandango_Stars"]
data_norm = data[cols]

fandango_distribution = data_norm["Fandango_Ratingvalue"].value_counts()
fandango_distribution = fandango_distribution.sort_index()

print(fandango_distribution.head(3))

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(data_norm["Fandango_Ratingvalue"], bins=30)
ax1.set_title = ("Distribution of Fandango Ratings")
ax1.set_xlabel("value")
ax1.set_ylabel("Distuibution")
ax1.set_ylim(0,50)#利用set_ylim()函数可以设定y轴的范围

ax2.hist(data_norm["RT_user_norm"], bins=40)
ax2.set_title = ("Distribution of RT_user_norm")
ax2.set_xlabel("value")
ax2.set_ylabel("Distuibution")
ax2.set_ylim(0,60)

ax3.hist(data_norm["Metacritic_user_nom"], bins=50)
ax3.set_title = ("Distribution of Metacritic_user_nom")
ax3.set_xlabel("value")
ax3.set_ylabel("Distuibution")
ax3.set_ylim(0,70)

ax4.hist(data_norm["IMDB_norm"], bins=60)
ax4.set_title = ("Distribution of IMDB_norm")
ax4.set_xlabel("value")
ax4.set_ylabel("Distuibution")
ax4.set_ylim(0,40)

plt.show()

---

制作象形图

import pandas as pd
import matplotlib.pyplot as plt

data = pd.read_csv("fandango_scores.csv")

cols = ["FILM", "RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue", "Fandango_Stars"]
data_norm = data[cols]

fig, ax = plt.subplots()

ax.boxplot(data_norm["RT_user_norm"])
ax.set_xticklabels(["Rotten Tomatoes"])
ax.set_ylim(0, 5)

plt.show()

将多个箱型图放在一张图上

import pandas as pd
import matplotlib.pyplot as plt

data = pd.read_csv("fandango_scores.csv")

cols = ["FILM", "RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue", "Fandango_Stars"]
data_norm = data[cols]
num_cols = ["RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue"]

fig, ax = plt.subplots()

ax.boxplot(data_norm[num_cols].values)#注意这里传入的需要是一个列表名，且取value
ax.set_xticklabels(["RT_user_norm", "Metacritic_user_nom", "IMDB_norm", "Fandango_Ratingvalue"])
ax.set_ylim(0, 5)

plt.show()

---

注意 fig,ax = plt.subplots() 意思是：建立一个fig对象，建立一个axis对象

等同于
fig=plt.figure()
ax=fig.add_subplot(111)