Task204:数据可视化

可视化部分的学习

import matplotlib.pyplot as plt
import numpy as np
fig=plt.figure()
ax=fig.add_subplot(1,1,1)
ax.plot(np.random.randn(1000).cumsum())
ticks=ax.set_xticks([0,250,500,750,1000])
labels=ax.set_xticklabels(['one','two','three','four','five'])
ax.set_title('My first matplotlib plot')
ax.set_xlabel('Stages')
plt.plot()
plt.show()

#多图汇聚在一图中
from numpy.random import randn
fig=plt.figure()
ax=fig.add_subplot(1,1,1)
ax.plot(randn(1000).cumsum(),'k',label='one')
ax.plot(randn(1000).cumsum(),'k--',label='two')
ax.plot(randn(1000).cumsum(),'k.',label='three')
ax.legend(loc='best')
plt.plot()
plt.show()

#在图表中添加图形
fig=plt.figure()
ax=fig.add_subplot(1,1,1)
rect=plt.Rectangle((0.2,0.75),0.4,0.15,color='k',alpha=0.3)
circ=plt.Circle((0.7,0.2),0.15,color='b',alpha=0.3)
pgon=plt.Polygon([[0.15,0.15],[0.35,0.4],[0.2,0.6]],color='g',alpha=0.5)
ax.add_patch(rect)
ax.add_patch(circ)
ax.add_patch(pgon)
plt.plot()
plt.show()
#plt.savefig('路径')

习题训练

#数据可视化
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

text=pd.read_csv('D:\\pythondata\\result.csv')
print(text.head(5))

#了解男女生存人数的分布
sex=text.groupby('Sex')['Survived'].sum()
sex.plot.bar()
plt.title('survived_count')
plt.show()

#男女中生存人与死亡人数的比例图
text.groupby(['Sex','Survived']) ['Survived'].count().unstack().plot(kind='bar',stacked=True)
plt.title('survived_count')
plt.ylabel('count')
#text(0,0.5,'count')

#数据集中表现不同票价的人生存和死亡人数的分布情况
fare_sur=text.groupby(['Fare'])['Survived'].value_counts().sort_values(ascending=False)
print(fare_sur)
fig=plt.figure(figsize=(20,18))
fare_sur.plot(grid=True)
plt.legend()
plt.show()
#排序前做折线图
fare_sur1=text.groupby(['Fare'])['Survived'].value_counts()
print(fare_sur1)
fig=plt.figure(figsize=(20,18))
fare_sur1.plot(grid=True)
plt.legend()
plt.show()