random_search.py

from sklearn.model_selection import train_test_split
import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import r2_score,mean_squared_error,mean_absolute_percentage_error
from sklearn.model_selection import GridSearchCV# Create the parameter grid based on the results of random search 
from sklearn.model_selection import RandomizedSearchCV# Number of trees in random forest

dataset = np.genfromtxt('data.csv', delimiter=',', skip_header=1)
x = dataset[:,[0,1,2,4,5,6,7,8,9]]
y = dataset[:,3]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=42)

n_estimators = [int(x) for x in np.linspace(start = 200, stop = 1000, num = 5)]
# Number of features to consider at every split
max_features = ['auto', 'sqrt']
# Maximum number of levels in tree
max_depth = [int(x) for x in np.linspace(10, 110, num = 11)]
max_depth.append(None)
# Minimum number of samples required to split a node
min_samples_split = [2, 5, 10]
# Minimum number of samples required at each leaf node
min_samples_leaf = [1, 2, 4]
# Method of selecting samples for training each tree
bootstrap = [True, False]# Create the random grid
random_grid = {'n_estimators': n_estimators,
               'max_features': max_features,
               'max_depth': max_depth,
               'min_samples_split': min_samples_split,
               'min_samples_leaf': min_samples_leaf,
               'bootstrap': bootstrap}
print(random_grid)
# Use the random grid to search for best hyperparameters
# First create the base model to tune
rf = RandomForestRegressor()
# Random search of parameters, using 3 fold cross validation, 
# search across 100 different combinations, and use all available cores
rf_random = RandomizedSearchCV(estimator = rf, param_distributions = random_grid, n_iter = 100, cv = 3, verbose=2, random_state=42, n_jobs = -1)# Fit the random search model
rf_random.fit(x_train, y_train)
rf_random.best_params_
print(rf_random.best_params_)