In [2]:
import pandas as pd
In [3]:
import statsmodels.formula.api as sm
In [4]:
iris=pd.read_csv("http://vincentarelbundock.github.io/Rdatasets/csv/datasets/iris.csv")
In [6]:
iris =iris.drop('Unnamed: 0', 1)
In [7]:
iris.head()
Out[7]:
In [15]:
iris.columns=['Sepal_Length', 'Sepal_Width', 'Petal_Length', 'Petal_Width',
'Species']
In [16]:
iris.columns
Out[16]:
In [17]:
result = sm.ols(formula="Sepal_Length ~ Petal_Length + Sepal_Width + Petal_Width + Species", data=iris)
In [18]:
result.fit()
Out[18]:
In [19]:
result.fit().summary()
Out[19]:
In [20]:
result.fit().params
Out[20]:
In [23]:
result.fit().outlier_test(method='bonf', alpha=0.05)
Out[23]:
In [ ]: