"""
Implementation and general notes:
• The parameters min_samples_split and min_impurity_decrease were difficult to analyse. Seems like smaller values are preferred
• The model often chose different hyperparemeters between runs. It seems inconsistent
"""
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import GridSearchCV
from utils import split_feats_targs, capture_features, capture_targets, export_results
(train_features, train_targets) = split_feats_targs('train_2.csv') # pass training set with targets
(val_features, val_targets) = split_feats_targs('val_2.csv') # pass validation set
test_features = capture_features('test_no_label_2.csv', False) # pass test set without targets
actual_targets = capture_targets('test_with_label_2.csv') # pass test set with targets
"""
Parameter options to tune:
• splitting criterion: gini and entropy
• maximum depth of the tree: 10 and no maximum
• minimum number of samples to split an internal node: experiment with values of your choice
• minimum impurity decrease: experiment with values of your choice
• class weight: None and balanced
"""
print("Finding best hyperparameters for DT....")
best_dt = GridSearchCV(DecisionTreeClassifier(), {
'criterion': ['gini', 'entropy'],
'max_depth': [10, None],
'min_samples_split': [2,3,5],
'min_impurity_decrease': [0.0, 1e-250, 1e-900],
'class_weight': [None, 'balanced']
from sklearn.neural_network import MLPClassifier
from utils import split_feats_targs, capture_features, capture_targets, export_results
(train_features, train_targets) = split_feats_targs(
'train_1.csv') # pass training set with targets
test_features = capture_features('test_no_label_1.csv',
False) # pass test set without targets
actual_targets = capture_targets(
'test_with_label_1.csv') # pass test set with targets
fitted_mlp = MLPClassifier(activation='logistic', solver='sgd').fit(
train_features, train_targets) # fits model with training set values
predicted_targets = list(fitted_mlp.predict(
test_features)) # gets predictions from model and record them
export_results(actual_targets, predicted_targets, 'Base-MLP-DS1.csv')
INTENDED FOR DEMO
Running this file will run every single estimator for the given training and test set
File inputs are required wherever <file_type> is seen
"""
from utils import split_feats_targs, capture_features, capture_targets, export_results
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import Perceptron
from sklearn.tree import DecisionTreeClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import GridSearchCV
"""
Store the necessary training/test set values into variables
"""
(train_features,
train_targets) = split_feats_targs('<demo_training_set_file_name>')
test_features = capture_features(
'<demo_test_set_file_name>',
False) # pass False if test set has no targets, otherwise pass True
actual_targets = capture_targets('<demo_test_set_w_targets_file_name>')
"""
Run GNB model
"""
fitted_gnb = GaussianNB().fit(
train_features, train_targets) # fit model with training set values
predicted_targets = list(fitted_gnb.predict(
test_features)) # get predictions from model and record them
export_results(actual_targets, predicted_targets, '<demo_output_file_name>')
"""
Run PER model
"""