def get_split_training_dataset(train_part=0.75):
""" Get the phy_train dataset shuffled and split """
# Impute dataset
X, Y, n, f = load_data("../data/raw/phy_train.dat")
# Split and shuffle
return train_test_split(X, Y, train_size=train_part)
def get_split_training_dataset(train_part=0.75):
""" Get the phy_train dataset shuffled and split """
# Impute dataset
X, Y, n, f = load_data("../data/raw/phy_train.dat")
# Split and shuffle
return train_test_split(X, Y, train_size=train_part)
def load_validation_data():
""" Load training and testing data
Returns
Xt -- Imputed training data
Yt -- training prediction
Xv -- Imputed validation data
"""
# Load and impute validation data
Xv, Yzero, nv, fv = load_data("../data/raw/phy_test.dat", load_y=False)
Xv = remove_features_missing_data(Xv)
# Load and impute training data
Xt, Yt, nt, ft = load_data("../data/raw/phy_train.dat")
Xt = remove_features_missing_data(Xt)
return Xt, Yt, Xv
def load_validation_data():
""" Load training and testing data
Returns
Xt -- Imputed training data
Yt -- training prediction
Xv -- Imputed validation data
"""
# Load and impute validation data
Xv, Yzero, nv, fv = load_data("../data/raw/phy_test.dat", load_y=False)
Xv = remove_features_missing_data(Xv)
# Load and impute training data
Xt, Yt, nt, ft = load_data("../data/raw/phy_train.dat")
Xt = remove_features_missing_data(Xt)
return Xt, Yt, Xv
import SVM as training
import imputation as imp
import K_means_imp as kimp
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import Normalizer, MinMaxScaler, StandardScaler
from sklearn import preprocessing
from sklearn.preprocessing import scale
import opti_svm as ops
import opti_forest as opf
if __name__ == '__main__':
raw_data = imp.load_data('cleaned_1-OCT-modelling.csv')
#nom = Normalizer(norm='l2')
#m = MinMaxScaler()
#s = StandardScaler()
no_missing, missing_set, index_no_missing, index_missing, labels, names = imp.deal_data(
raw_data)
X_set, y = imp.impute(no_missing, missing_set, index_missing, labels,
names, raw_data)
X_train, X_test, y_train, y_test = train_test_split(X_set,
y,
train_size=0.8,
random_state=1)
#X_strain,X_stest,y_strain,y_stest = train_test_split(X_norm, y, train_size=0.8, random_state=1)
svc_precision, svc_recall, svc_f1 = training.svm(X_train, y_train, X_test,
y_test)
#training.svm(X_strain, y_strain, X_stest, y_stest)
print('svc_precision for each labels:', svc_precision, '\n')
print('svc_recall for each labels:', svc_recall, '\n')
print('svc_f1 for each labels:', svc_f1, '\n')
""" Use entirety of provided X, Y to predict
Default Arguments
Xtrain -- Training data
Ytrain -- Training prediction
Named Arguments
--
Returns
classifier -- a tree fitted to Xtrain and Ytrain
"""
classifier = KNeighborsClassifier(125)
classifier.fit(Xtrain, Ytrain)
return classifier
if __name__ == "__main__":
# Let's take our training data and train a decision tree
# on a subset. Scikit-learn provides a good module for cross-
# validation.
if len(sys.argv) < 2:
print "Usage: $ python decision-tree.py /path/to/data/file/"
else:
training = sys.argv[1]
X,Y,n,f = load_data(training)
Xt, Xv, Yt, Yv = shuffle_split(X,Y)
Classifier = train(Xt, Yt)
print "KNN Accuracy"
suite(Yv, Classifier.predict(Xv))
def classify(Xtrain, Ytrain):
""" Use entirety of provided X, Y to predict
Arguments
Xtrain -- Training data
Ytrain -- Training prediction
Returns
ready_tree -- a tree fitted to Xtrain and Ytrain
"""
ready_tree = tree.DecisionTreeClassifier()
ready_tree.fit(Xtrain, Ytrain)
return ready_tree
if __name__ == "__main__":
# Let's take our training data and train a decision tree
# on a subset. Scikit-learn provides a good module for cross-
# validation.
if len(sys.argv) < 2:
print "Usage: $ python decision-tree.py /path/to/data/file/"
else:
training = sys.argv[1]
X, Y, n, f = load_data(training)
Xt, Xv, Yt, Yv = shuffle_split(X, Y)
tree = classify(Xt, Yt)
print "Decision Tree Accuracy:", acc(Yv, tree.predict(Xv)), "%"
