Created
October 11, 2018 16:59
-
-
Save socratesk/485e267b875b885024211b158301de99 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# import libraries | |
import numpy as np | |
import pandas as pd | |
import eli5 | |
from sklearn.ensemble import RandomForestRegressor | |
from sklearn.model_selection import train_test_split | |
from eli5.sklearn import PermutationImportance | |
# load data file | |
train = pd.read_csv('50-Startups.csv') | |
# perform one-hot encoding for categorical variable | |
trainDummies = pd.get_dummies(train['State'], prefix = 'state') | |
# combine original and one-hot encoded dataframes together | |
train = pd.concat([train, trainDummies], axis=1) | |
# extract dependent (predictor) feature | |
y = train.Profit | |
# extract independent features from combined dataframe by removing unwanted features | |
X = train.drop(["Profit", "State", "state_New York"], axis=1) | |
# split train and validation datasets | |
train_X, val_X, train_y, val_y = train_test_split(X, y, random_state=5) | |
# create Random Forest Regressor model and fit dependent and independent features | |
rf_model = RandomForestRegressor(random_state=0).fit(train_X, train_y) | |
# compute Permutation Importance using Random Forest Regressor model on validation dataset | |
permImportance = PermutationImportance(rf_model, random_state=0).fit(val_X, val_y) | |
# print computer feature weights | |
eli5.show_weights(permImportance, feature_names = X.columns.tolist()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment