katiedave / dsc-1-11-13-adjusted-r-squared-lab-online-ds-sp-000 Goto Github PK

import pandas as pd
import numpy as np
from sklearn.datasets import load_boston
boston = load_boston()

boston_features = pd.DataFrame(boston.data, columns = boston.feature_names)
boston_features = boston_features.drop(["NOX","ZN"],axis=1)

# first, create bins for based on the values observed. 3 values will result in 2 bins
bins = [0,6,  24]
bins_rad = pd.cut(boston_features['RAD'], bins)
bins_rad = bins_rad.cat.as_unordered()

# first, create bins for based on the values observed. 4 values will result in 3 bins
bins = [0, 270, 360, 712]
bins_tax = pd.cut(boston_features['TAX'], bins)
bins_tax = bins_tax.cat.as_unordered()

tax_dummy = pd.get_dummies(bins_tax, prefix="TAX")
rad_dummy = pd.get_dummies(bins_rad, prefix="RAD")
boston_features = boston_features.drop(["RAD","TAX"], axis=1)
boston_features = pd.concat([boston_features, rad_dummy, tax_dummy], axis=1)

age = boston_features["AGE"]
b = boston_features["B"]
logcrim = np.log(boston_features["CRIM"])
logdis = np.log(boston_features["DIS"])
logindus = np.log(boston_features["INDUS"])
loglstat = np.log(boston_features["LSTAT"])
logptratio = np.log(boston_features["PTRATIO"])

# minmax scaling
boston_features["B"] = (b-min(b))/(max(b)-min(b))
boston_features["CRIM"] = (logcrim-min(logcrim))/(max(logcrim)-min(logcrim))
boston_features["DIS"] = (logdis-min(logdis))/(max(logdis)-min(logdis))

#standardization
boston_features["AGE"] = (age-np.mean(age))/np.sqrt(np.var(age))
boston_features["INDUS"] = (logindus-np.mean(logindus))/np.sqrt(np.var(logindus))
boston_features["LSTAT"] = (loglstat-np.mean(loglstat))/np.sqrt(np.var(loglstat))
boston_features["PTRATIO"] = (logptratio-np.mean(logptratio))/(np.sqrt(np.var(logptratio)))

import statsmodels.api as sm

def stepwise_selection(X, y, 
                       initial_list=[], 
                       threshold_in=0.01, 
                       threshold_out = 0.05, 
                       verbose=True):
    """ Perform a forward-backward feature selection 
    based on p-value from statsmodels.api.OLS
    Arguments:
        X - pandas.DataFrame with candidate features
        y - list-like with the target
        initial_list - list of features to start with (column names of X)
        threshold_in - include a feature if its p-value < threshold_in
        threshold_out - exclude a feature if its p-value > threshold_out
        verbose - whether to print the sequence of inclusions and exclusions
    Returns: list of selected features 
    Always set threshold_in < threshold_out to avoid infinite looping.
    See https://en.wikipedia.org/wiki/Stepwise_regression for the details
    """
    included = list(initial_list)
    while True:
        changed=False
        # forward step
        excluded = list(set(X.columns)-set(included))
        new_pval = pd.Series(index=excluded)
        for new_column in excluded:
            model = sm.OLS(y, sm.add_constant(pd.DataFrame(X[included+[new_column]]))).fit()
            new_pval[new_column] = model.pvalues[new_column]
        best_pval = new_pval.min()
        if best_pval < threshold_in:
            best_feature = new_pval.idxmin()
            included.append(best_feature)
            changed=True
            if verbose:
                print('Add  {:30} with p-value {:.6}'.format(best_feature, best_pval))

        # backward step
        model = sm.OLS(y, sm.add_constant(pd.DataFrame(X[included]))).fit()
        # use all coefs except intercept
        pvalues = model.pvalues.iloc[1:]
        worst_pval = pvalues.max() # null if pvalues is empty
        if worst_pval > threshold_out:
            changed=True
            worst_feature = pvalues.argmax()
            included.remove(worst_feature)
            if verbose:
                print('Drop {:30} with p-value {:.6}'.format(worst_feature, worst_pval))
        if not changed:
            break
    return included