Using the data from the 2013_NYC_CD_MedianIncome_Recycle.xlsx file, create a predictor using the weights from the model. This time, use the built in attributes in your model rather than hard-coding them into your algorithm
In [1]:
import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt # package for doing plotting (necessary for adding the line)
import statsmodels.formula.api as smf # package we'll be using for linear regression
In [27]:
df = pd.read_excel("2013_NYC_CD_MedianIncome_Recycle.xlsx")
In [28]:
lm = smf.ols(formula="RecycleRate~MdHHIncE",data=df).fit() #notice the formula regresses Y on X (Y~X)
intercept, slope = lm.params
lm.params
df.plot(kind='scatter', x='MdHHIncE', y='RecycleRate')
Out[28]:
In [24]:
plt.plot(df['MdHHIncE'], slope*df["MdHHIncE"]+intercept,"-",color="blue") #we create the best fit line from the values in the fit model
Out[24]:
In [ ]:
In [ ]:
In [ ]: