In [1]:
%matplotlib inline
# -*- coding: utf-8 -*-
"""
Created on Mon Dec 14 16:26:46 2015
@author: jrose01
"""
#from pandas import Series, DataFrame
import pandas as pd
import numpy as np
import matplotlib.pylab as plt
from sklearn.cross_validation import train_test_split
from sklearn.linear_model import LassoLarsCV
#Load the dataset
data = pd.read_csv("C:/Users/JD87417/Desktop/python work/Coursera/tree_addhealth.csv")
#upper-case all DataFrame column names
data.columns = map(str.upper, data.columns)
# Data Management
data_clean = data.dropna()
recode1 = {1:1, 2:0}
data_clean['MALE']= data_clean['BIO_SEX'].map(recode1)
#select predictor variables and target variable as separate data sets
predvar= data_clean[['MALE','HISPANIC','WHITE','BLACK','NAMERICAN','ASIAN',
'AGE','ALCEVR1','ALCPROBS1','MAREVER1','COCEVER1','INHEVER1','CIGAVAIL','DEP1',
'ESTEEM1','VIOL1','PASSIST','DEVIANT1','GPA1','EXPEL1','FAMCONCT','PARACTV',
'PARPRES']]
target = data_clean.SCHCONN1
# standardize predictors to have mean=0 and sd=1
predictors=predvar.copy()
from sklearn import preprocessing
predictors['MALE']=preprocessing.scale(predictors['MALE'].astype('float64'))
predictors['HISPANIC']=preprocessing.scale(predictors['HISPANIC'].astype('float64'))
predictors['WHITE']=preprocessing.scale(predictors['WHITE'].astype('float64'))
predictors['NAMERICAN']=preprocessing.scale(predictors['NAMERICAN'].astype('float64'))
predictors['ASIAN']=preprocessing.scale(predictors['ASIAN'].astype('float64'))
predictors['AGE']=preprocessing.scale(predictors['AGE'].astype('float64'))
predictors['ALCEVR1']=preprocessing.scale(predictors['ALCEVR1'].astype('float64'))
predictors['ALCPROBS1']=preprocessing.scale(predictors['ALCPROBS1'].astype('float64'))
predictors['MAREVER1']=preprocessing.scale(predictors['MAREVER1'].astype('float64'))
predictors['COCEVER1']=preprocessing.scale(predictors['COCEVER1'].astype('float64'))
predictors['INHEVER1']=preprocessing.scale(predictors['INHEVER1'].astype('float64'))
predictors['CIGAVAIL']=preprocessing.scale(predictors['CIGAVAIL'].astype('float64'))
predictors['DEP1']=preprocessing.scale(predictors['DEP1'].astype('float64'))
predictors['ESTEEM1']=preprocessing.scale(predictors['ESTEEM1'].astype('float64'))
predictors['VIOL1']=preprocessing.scale(predictors['VIOL1'].astype('float64'))
predictors['PASSIST']=preprocessing.scale(predictors['PASSIST'].astype('float64'))
predictors['DEVIANT1']=preprocessing.scale(predictors['DEVIANT1'].astype('float64'))
predictors['GPA1']=preprocessing.scale(predictors['GPA1'].astype('float64'))
predictors['EXPEL1']=preprocessing.scale(predictors['EXPEL1'].astype('float64'))
predictors['FAMCONCT']=preprocessing.scale(predictors['FAMCONCT'].astype('float64'))
predictors['PARACTV']=preprocessing.scale(predictors['PARACTV'].astype('float64'))
predictors['PARPRES']=preprocessing.scale(predictors['PARPRES'].astype('float64'))
# split data into train and test sets
pred_train, pred_test, tar_train, tar_test = train_test_split(predictors, target,
test_size=.3, random_state=123)
# specify the lasso regression model
model=LassoLarsCV(cv=10, precompute=False).fit(pred_train,tar_train)
# print variable names and regression coefficients
dict(zip(predictors.columns, model.coef_))
# plot coefficient progression
m_log_alphas = -np.log10(model.alphas_)
ax = plt.gca()
plt.plot(m_log_alphas, model.coef_path_.T)
plt.axvline(-np.log10(model.alpha_), linestyle='--', color='k',
label='alpha CV')
plt.ylabel('Regression Coefficients')
plt.xlabel('-log(alpha)')
plt.title('Regression Coefficients Progression for Lasso Paths')
# plot mean square error for each fold
m_log_alphascv = -np.log10(model.cv_alphas_)
plt.figure()
plt.plot(m_log_alphascv, model.cv_mse_path_, ':')
plt.plot(m_log_alphascv, model.cv_mse_path_.mean(axis=-1), 'k',
label='Average across the folds', linewidth=2)
plt.axvline(-np.log10(model.alpha_), linestyle='--', color='k',
label='alpha CV')
plt.legend()
plt.xlabel('-log(alpha)')
plt.ylabel('Mean squared error')
plt.title('Mean squared error on each fold')
# MSE from training and test data
from sklearn.metrics import mean_squared_error
train_error = mean_squared_error(tar_train, model.predict(pred_train))
test_error = mean_squared_error(tar_test, model.predict(pred_test))
print ('training data MSE')
print(train_error)
print ('test data MSE')
print(test_error)
# R-square from training and test data
rsquared_train=model.score(pred_train,tar_train)
rsquared_test=model.score(pred_test,tar_test)
print ('training data R-square')
print(rsquared_train)
print ('test data R-square')
print(rsquared_test)
In [ ]: