nile-baseline.py

import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import BaggingClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import BernoulliNB
from sklearn.naive_bayes import MultinomialNB
from sklearn import metrics
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import Imputer
from sklearn.model_selection import train_test_split
import numpy as np


def get_naive_bayes_models():
    gnb = GaussianNB()
    mnb = MultinomialNB()
    bnb = BernoulliNB()
    classifier_list = [gnb,mnb,bnb]
    classifier_name_list = ['Gaussian NB','Multinomial NB','Bernoulli NB']
    return classifier_list,classifier_name_list


def get_neural_network(hidden_layer_size=50):
    mlp = MLPClassifier(hidden_layer_sizes=hidden_layer_size)
    return [mlp], ['MultiLayer Perceptron']


def get_ensemble_models():
    rf = RandomForestClassifier(n_estimators=51,min_samples_leaf=5,min_samples_split=3)
    bagg = BaggingClassifier(n_estimators=71,random_state=42)
    extra = ExtraTreesClassifier(n_estimators=57,random_state=42)
    ada = AdaBoostClassifier(n_estimators=51,random_state=42)
    grad = GradientBoostingClassifier(n_estimators=101,random_state=42)
    classifier_list = [rf,bagg,extra,ada,grad]
    classifier_name_list = ['Random Forests','Bagging','Extra Trees','AdaBoost','Gradient Boost']
    return classifier_list,classifier_name_list


def label_encode_frame(dataframe):
    columns = dataframe.columns
    encoder = LabelEncoder()
    for column in columns:
        if type(dataframe[column][0]) is str:
            dataframe[column] = encoder.fit_transform(dataframe[column].values)
    return dataframe


def spilt_date(list_of_date_string,separator='-',format='yyyy-mm-dd'):
    month_list = list([])
    day_list = list([])
    year_list = list([])
    for date_string in list_of_date_string:
        date_list = date_string.strip().split(separator)
        month_list.append(int(date_list[1]))
        day_list.append(int(date_list[2]))
        year_list.append(int(date_list[0]))
    return month_list,day_list,year_list


def print_evaluation_metrics(trained_model,trained_model_name,X_test,y_test):
    print '--------- For Model : ', trained_model_name,'-----------------'
    predicted_values = trained_model.predict(X_test)
    print metrics.classification_report(y_test,predicted_values)
    print "Accuracy Score : ", metrics.accuracy_score(y_test,predicted_values)
    print "---------------------------------------\n"


filename = 'train.csv'
train_frame = pd.read_csv(filename)
train_frame['month'], train_frame['day'], train_frame['year'] = spilt_date(list(train_frame['Date'].values))
target_classes = list(train_frame['WnvPresent'].values)
del train_frame['Date']
del train_frame['WnvPresent']
train_frame = label_encode_frame(train_frame)
X_train,X_test,y_train,y_test = train_test_split(train_frame.values,target_classes,test_size=0.2,random_state=42)
classifier_list,classifier_name_list = get_ensemble_models()
for classifier,classifier_name in zip(classifier_list,classifier_name_list):
    classifier.fit(X_train,y_train)
    print_evaluation_metrics(classifier,classifier_name,X_test,y_test)