Matplotlib 库是 python 的数据可视化库
import matplotlib.pyplot as plt
1、字符串转化为日期
unrate = pd.read_csv("unrate.csv")
unrate["DATE"] = pd.to_datetime(unrate["DATE"])
2、拆线图
data1 = unrate[0: 12]
plt.plot(data1["DATE"], data1["VALUE"]) # x轴数据和y轴数据
plt.xticks(rotation = 45) # 将x轴的属性旋转一个角度
plt.xlabel("Date Month") # x轴描述
plt.ylabel("Rate Value") # y轴描述
plt.title("my first plt") # 标题
plt.show()
3、多图拼切
fig = plt.figure()
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()
4、一图多线
fig = plt.figure(figsize=(6, 3)) # 设定图尺寸 data1 = unrate[0: 12]
data1["MONTH"] = data1["DATE"].dt.month
plt.plot(data1["MONTH"], data1["VALUE"], c="red") data2 = unrate[12: 24]
data2["MONTH"] = data2["DATE"].dt.month
plt.plot(data2["MONTH"], data2["VALUE"], c="blue") plt.xticks(rotation = 45) #将x轴的属性旋转一个角度
plt.xlabel("Date Month")
plt.ylabel("Rate Value")
plt.title("my first plt")
plt.show()
5、一图多线 - 自动跑代码（带图例）
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')
plt.legend(loc = 'upper left') # 位置
plt.show()
6、条形图
fand_col = ["Fandango_Stars", "Fandango_Ratingvalue", "Metacritic_norm", "RT_user_norm_round", "IMDB_norm_round"] bar_heights = fand_new.ix[0, fand_col].values # 条形图高度
bar_positions = np.arange(5) + 0.75 # 条形图起始位置
tick_positions = range(1, 6)
fig, ax = plt.subplots() ax.bar(bar_positions, bar_heights, 0.5) # 0.5表示条形图的宽度
ax.set_xticks(tick_positions)
ax.set_xticklabels(fand_col, rotation = 90) ax.set_xlabel('Rating Source')
ax.set_ylabel('Average Rating')
ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)')
plt.show()
7、条形图 - 横向
fand_col = ["Fandango_Stars", "Fandango_Ratingvalue", "Metacritic_norm", "RT_user_norm_round", "IMDB_norm_round"]
bar_heights = fand_new.ix[0, fand_col].values
bar_positions = np.arange(5) + 0.75
tick_positions = range(1, 6)
fig, ax = plt.subplots() ax.barh(bar_positions, bar_heights, 0.5) # 横向
ax.set_yticks(tick_positions)
ax.set_yticklabels(fand_col, rotation = 0) ax.set_xlabel('Rating Source')
ax.set_ylabel('Average Rating')
ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)')
plt.show()
8、散点图
fig, ax = plt.subplots()
ax.scatter(fand_new['Fandango_Stars'], fand_new['Metacritic_norm']) # 散点图
ax.set_xlabel('Fandango')
ax.set_ylabel('Rotten Tomatoes')
plt.show()
9、直方图
fandango_distribution = fand_new['Fandango_Stars'].value_counts()
fandango_distribution = fandango_distribution.sort_index()
imdb_distribution = fand_new['IMDB_norm_round'].value_counts()
imdb_distribution = imdb_distribution.sort_index() # bins 是什么？通俗一点就是分组，将N多数据分成X组。默认：bins=10
fig, ax = plt.subplots()
ax.hist(fand_new['Fandango_Stars'], range=(4, 5), bins=5) # range 需要查看x轴的范围
plt.show()
10、多图
fig = plt.figure(figsize=(12, 12))
ax1 = fig.add_subplot(2,2,1)
ax2 = fig.add_subplot(2,2,2)
ax3 = fig.add_subplot(2,2,3)
ax4 = fig.add_subplot(2,2,4)
ax1.hist(fand_new['Fandango_Stars'], bins=20, range=(0, 5))
ax1.set_title('Distribution of Fandango Ratings')
ax1.set_ylim(0, 50) ax2.hist(fand_new['IMDB_norm_round'], 20, range=(0, 5))
ax2.set_title('Distribution of Rotten Tomatoes Ratings')
ax2.set_ylim(0, 50) ax3.hist(fand_new['Metacritic_norm'], 20, range=(0, 5))
ax3.set_title('Distribution of Metacritic Ratings')
ax3.set_ylim(0, 50) ax4.hist(fand_new['RT_user_norm_round'], 20, range=(0, 5))
ax4.set_title('Distribution of IMDB Ratings')
ax4.set_ylim(0, 50) plt.show()
11、四分图
fig, ax = plt.subplots() ax.boxplot(fand_new['Metacritic_norm'])
ax.set_xticklabels(['Rotten Tomatoes'])
ax.set_ylim(0, 5) plt.show()
12、多图 - 通过数组
num_cols = ['Fandango_Stars', 'IMDB_norm_round', 'Metacritic_norm', 'RT_user_norm_round']
fig, ax = plt.subplots() ax.boxplot(fand_new[num_cols].values)
ax.set_xticklabels(num_cols, rotation=90)
ax.set_ylim(0, 5) plt.show()
13、数据可视化 - 简洁一些
fig, ax = plt.subplots() ax.plot(women_degrees['Year'], women_degrees['Biology'], c='blue', label='Women')
ax.plot(women_degrees['Year'], 100-women_degrees['Biology'], c='green', label='Men')
ax.tick_params(bottom="off", top="off", left="off", right="off") # 可配置参数 for key,spine in ax.spines.items():
spine.set_visible(False) ax.legend(loc='upper right') plt.show()
14、数据可视化 - 多图 - 通过程序
major_cats = ['Biology', 'Computer Science', 'Engineering', 'Math and Statistics'] fig = plt.figure(figsize=(12, 12)) for sp in range(0, 4):
ax = fig.add_subplot(2, 2, sp+1)
ax.plot(women_degrees['Year'], women_degrees[major_cats[sp]], c='blue', label='Women')
ax.plot(women_degrees['Year'], 100-women_degrees[major_cats[sp]], c='green', label='Men') plt.legend(loc='upper right')
plt.show()
15、数据可视化 - 多图 - 通过程序跑 - 多图 简洁
major_cats = ['Biology', 'Computer Science', 'Engineering', 'Math and Statistics'] fig = plt.figure(figsize=(12, 12)) for sp in range(0, 4):
ax = fig.add_subplot(2, 2, sp+1)
ax.plot(women_degrees['Year'], women_degrees[major_cats[sp]], c='blue', label='Women')
ax.plot(women_degrees['Year'], 100-women_degrees[major_cats[sp]], c='green', 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()
16、如何使图表更好看？
cb_dark_blue = (0/255, 107/255, 164/255) # 自定义颜色
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)
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()
17、加粗线
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, 4):
ax = fig.add_subplot(1, 4, sp+1)
ax.plot(women_degrees['Year'], women_degrees[major_cats[sp]], c=cb_dark_blue, label='Women', linewidth=3) # 线条粗细
ax.plot(women_degrees['Year'], 100-women_degrees[major_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(major_cats[sp])
ax.tick_params(bottom="off", top="off", left="off", right="off") plt.legend(loc='upper right')
plt.show()
18、加注释
fig = plt.figure(figsize=(18, 3)) for sp in range(0, 4):
ax = fig.add_subplot(1, 4, sp+1)
ax.plot(women_degrees['Year'], women_degrees[major_cats[sp]], c=cb_dark_blue, label='Women', linewidth=3)
ax.plot(women_degrees['Year'], 100-women_degrees[major_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(major_cats[sp])
ax.tick_params(bottom="off", top="off", left="off", right="off") if sp == 0:
ax.text(2005, 87, 'Men') # 注释
ax.text(2002, 8, 'Women')
elif sp == 3:
ax.text(2005, 62, 'Men')
ax.text(2001, 35, 'Women') plt.show()