Thesis-NoiseDetection-26-attributes/train_model.py

from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier, VotingClassifier

import sklearn.svm as svm
from sklearn.utils import shuffle
from sklearn.externals import joblib
from sklearn.metrics import accuracy_score, f1_score
from sklearn.model_selection import cross_val_score

import numpy as np
import pandas as pd
import sys, os, getopt

from modules.utils import config as cfg
from modules import models as mdl

saved_models_folder = cfg.saved_models_folder
models_list         = cfg.models_names_list

current_dirpath = os.getcwd()
output_model_folder = os.path.join(current_dirpath, saved_models_folder)


def main():

    # TODO : use argparse
    
    if len(sys.argv) <= 2:
        print('python train_model.py --data xxxx --output xxxx --choice svm_model')
        sys.exit(2)
    try:
        opts, args = getopt.getopt(sys.argv[1:], "hd:o:c", ["help=", "data=", "output=", "choice="])
    except getopt.GetoptError:
        # print help information and exit:
        print('python train_model.py --data xxxx --output xxxx --choice svm_model')
        sys.exit(2)
    for o, a in opts:
        if o == "-h":
            print('python train_model.py --data xxxx --output xxxx --choice svm_model')
            sys.exit()
        elif o in ("-d", "--data"):
            p_data_file = a
        elif o in ("-o", "--output"):
            p_output = a
        elif o in ("-c", "--choice"):
            p_choice = a

            if not p_choice in models_list:
                assert False, "Unknown model choice"

        else:
            assert False, "unhandled option"

    if not os.path.exists(output_model_folder):
        os.makedirs(output_model_folder)

    ########################
    # 1. Get and prepare data
    ########################
    dataset_train = pd.read_csv(p_data_file + '.train', header=None, sep=";")
    dataset_test = pd.read_csv(p_data_file + '.test', header=None, sep=";")

    # default first shuffle of data
    dataset_train = shuffle(dataset_train)
    dataset_test = shuffle(dataset_test)

    # get dataset with equal number of classes occurences
    noisy_df_train = dataset_train[dataset_train.ix[:, 0] == 1]
    not_noisy_df_train = dataset_train[dataset_train.ix[:, 0] == 0]
    nb_noisy_train = len(noisy_df_train.index)

    noisy_df_test = dataset_test[dataset_test.ix[:, 0] == 1]
    not_noisy_df_test = dataset_test[dataset_test.ix[:, 0] == 0]
    nb_noisy_test = len(noisy_df_test.index)

    final_df_train = pd.concat([not_noisy_df_train[0:nb_noisy_train], noisy_df_train])
    final_df_test = pd.concat([not_noisy_df_test[0:nb_noisy_test], noisy_df_test])

    # shuffle data another time
    final_df_train = shuffle(final_df_train)
    final_df_test = shuffle(final_df_test)

    final_df_train_size = len(final_df_train.index)
    final_df_test_size = len(final_df_test.index)

    # use of the whole data set for training
    x_dataset_train = final_df_train.ix[:,1:]
    x_dataset_test = final_df_test.ix[:,1:]

    y_dataset_train = final_df_train.ix[:,0]
    y_dataset_test = final_df_test.ix[:,0]

    #######################
    # 2. Construction of the model : Ensemble model structure
    #######################

    print("-------------------------------------------")
    print("Train dataset size: ", final_df_train_size)
    model = mdl.get_trained_model(p_choice, x_dataset_train, y_dataset_train)

    #######################
    # 3. Fit model : use of cross validation to fit model
    #######################
    val_scores = cross_val_score(model, x_dataset_train, y_dataset_train, cv=5)
    print("Accuracy: %0.2f (+/- %0.2f)" % (val_scores.mean(), val_scores.std() * 2))

    ######################
    # 4. Test : Validation and test dataset from .test dataset
    ######################

    # we need to specify validation size to 20% of whole dataset
    val_set_size = int(final_df_train_size/3)
    test_set_size = val_set_size

    total_validation_size = val_set_size + test_set_size

    if final_df_test_size > total_validation_size:
        x_dataset_test = x_dataset_test[0:total_validation_size]
        y_dataset_test = y_dataset_test[0:total_validation_size]

    X_test, X_val, y_test, y_val = train_test_split(x_dataset_test, y_dataset_test, test_size=0.5, random_state=1)

    y_test_model = model.predict(X_test)
    y_val_model = model.predict(X_val)

    val_accuracy = accuracy_score(y_val, y_val_model)
    test_accuracy = accuracy_score(y_test, y_test_model)

    val_f1 = f1_score(y_val, y_val_model)
    test_f1 = f1_score(y_test, y_test_model)


    ###################
    # 5. Output : Print and write all information in csv
    ###################

    print("Validation dataset size ", val_set_size)
    print("Validation: ", val_accuracy)
    print("Validation F1: ", val_f1)
    print("Test dataset size ", test_set_size)
    print("Test: ", val_accuracy)
    print("Test F1: ", test_f1)


    ##################
    # 6. Save model : create path if not exists
    ##################

    if not os.path.exists(saved_models_folder):
        os.makedirs(saved_models_folder)

    joblib.dump(model, output_model_folder + '/' + p_output + '.joblib')

if __name__== "__main__":
    main()