資料分析彙總學習

import pandas as pd
import numpy as np
from pandas import Series, DataFrame
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

# 開啟一個花瓣長寬資料檔案
f = open('iris.csv')
iris = pd.read_csv(f)
iris.head()


SepalLength SepalWidth  PetalLength PetalWidth  Name
0   5.1 3.5 1.4
 
 0.2 Iris-setosa
1   4.9 3.0 1.4 0.2 Iris-setosa
2   4.7 3.2 1.3 0.2 Iris-setosa
3   4.6 3.1 1.5 0.2 Iris-setosa
4   5.0 3.6 1.4 0.2 Iris-setosa

# 繪製的顏色字典,zip傳入倆個列表
iris.Name.unique()
array(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'], dtype=object)
color_map = dict(zip(iris.Name.unique(), ['blue'
 
,'green','red']))

使用matplot

for species, group in iris.groupby('Name'):
    plt.scatter(group['PetalLength'], group['SepalLength'],
               color=color_map[species],
               alpha=0.3,edgecolor=None,
               label=species)
plt.legend(frameon=True, title='Name')
plt.xlabel('PetalLength'
 
)
plt.ylabel('SepalLength')

使用Seaborn

sns.lmplot('PetalLength','SepalLength',iris,hue='Name', fit_reg=False)