Trying to run the below code for boston housing linear regression analysis:
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import scipy.stats as stats
import sklearn
from sklearn.datasets import load_boston
%matplotlib inline
boston = load_boston() #Load the dataset
#This creates a dictionary that has data inside of it. ls look at the keys of this dictionary
print boston.keys()
#print boston.data
#So this a matrix of datapoints.
print boston.data.shape
#We have 506 rows and 13 columns
#Lets see if we can learn more about these 506 rows
print boston.DESCR
boston_df = pd.DataFrame(boston.data)
boston_df.head()
boston_df.columns = boston.feature_names
boston_df.head()
boston_df.describe()
X = boston_df
y = boston.target
from sklearn.linear_model import LinearRegression
lm = LinearRegression()
lm.fit(X, y)
print 'Estimated intercept coefficent:', lm.intercept_
print 'Number of coefficients:', len(lm.coef_)
pd.DataFrame(zip(boston_df.columns, lm.coef_), columns=['feature', 'coefficient'])
print "Predicted House price", lm.predict(X)[41] * 1000
print "Equation house price", (lm.intercept_ + np.dot(lm.coef_, X.iloc[[41]].values[0])) * 1000
print "Target price", y[41] * 1000
print "Residual price", (lm.predict(X)[41] - y[41]) * 1000
print "R^2 =", lm.score(X, y)
plt.scatter(y, lm.predict(X))
plt.xlabel('Prices: $Y_i$')
plt.ylabel('PredictedPrices: $\hat{Y}_i$')
plt.title('Actual vs Predicted')
plt.plot()
Keep getting this exit error each time:
lm = LinearRegression()
lm.fit(X, y)
Engine exited with status 2.
