def __init__(self, data_path='Bike-Sharing-Dataset/hour.csv'):
'''Initialize the random forest model.
Keyword Arguments:
data_path {str} -- Path to the Bike Sharing Dataset. (default: {'Bike-Sharing-Dataset/hour.csv'})
'''
# Make results reproducible
random.seed(100)
# Load data form bike sharing csv
self.data = {}
dataloader = Dataloader(data_path)
self.data['full'] = dataloader.getFullData()
# Define feature and target variables
self.features= ['season', 'mnth', 'hr', 'holiday', 'weekday', 'workingday', 'weathersit', 'temp', 'atemp', 'hum', 'windspeed']
self.target = ['cnt']
# Convert pandas frame into samples and labels
self.samples, self.labels = {}, {}
self.samples['full'] = self.data['full'][self.features].values
self.labels['full'] = self.data['full'][self.target].values.ravel()
# Define model
self.model = RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,
max_features='auto', max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=4,
min_weight_fraction_leaf=0.0, n_estimators=200, n_jobs=None,
oob_score=False, random_state=100, verbose=0, warm_start=False)
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.linear_model import LinearRegression
import random
%matplotlib inline
random.seed(100)
dataloader = Dataloader('Bike-Sharing-Dataset/hour.csv')
train, val, test = dataloader.getData()
fullData = dataloader.getFullData()
category_features = ['season', 'holiday', 'mnth', 'hr', 'weekday', 'workingday', 'weathersit']
number_features = ['temp', 'atemp', 'hum', 'windspeed']
features= category_features + number_features
target = ['cnt']
sns.set(font_scale=1.0)
fig, axes = plt.subplots(nrows=3,ncols=2)
fig.set_size_inches(15, 15)
sns.boxplot(data=train,y="cnt",orient="v",ax=axes[0][0])
sns.boxplot(data=train,y="cnt",x="mnth",orient="v",ax=axes[0][1])
sns.boxplot(data=train,y="cnt",x="weathersit",orient="v",ax=axes[1][0])
sns.boxplot(data=train,y="cnt",x="workingday",orient="v",ax=axes[1][1])
sns.boxplot(data=train,y="cnt",x="hr",orient="v",ax=axes[2][0])
sns.boxplot(data=train,y="cnt",x="temp",orient="v",ax=axes[2][1])