def KNN(X, y):
X_t, X_test, y_t, y_test = train_test_split(X,
y,
test_size=1 / 4,
random_state=0)
X_train, y_train = GSMOTE.OverSample(X_t, y_t)
# X_train,y_train = X_t,y_t
# Fitting Simple Linear Regression to the Training set
classifier = KNeighborsClassifier(n_neighbors=5, metric='minkowski', p=2)
classifier.fit(X_train, y_train)
# Predicting the Test set results
y_pred = classifier.predict(X_test).astype(int)
evaluate("KNN", y_test, y_pred)
def decision_tree(X, y):
X_t, X_test, y_t, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=0)
X_train, y_train = GSMOTE.OverSample(X_t, y_t)
# Fitting Simple Linear Regression to the Training set
regressor = DecisionTreeRegressor()
regressor.fit(X_train, y_train)
# Predicting the Test set results
y_predict = regressor.predict(X_test)
y_pred = np.where(y_predict > 0.5, 1, 0)
evaluate("Decision Tree", y_test, y_pred)
def gradient_boosting(X, y):
X_t, X_test, y_t, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=0)
X_train, y_train = GSMOTE.OverSample(X_t, y_t)
# Fitting Gradient boosting
gbc = GradientBoostingClassifier(n_estimators=100,
learning_rate=0.01,
max_depth=3)
gbc.fit(X_train, y_train)
# Predicting the Test set results
y_predict = gbc.predict(X_test)
y_pred = np.where(y_predict.astype(int) > 0.5, 1, 0)
evaluate("Gradient Boosting", y_test, y_pred)
def linear_training(X, y):
X_t, X_test, y_t, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=0)
# Visualize original data
vs(X_t, y_t, "Original data")
# oversample
X_train, y_train = GSMOTE.OverSample(X_t, y_t)
# visualize oversampled data
vs(X_train, y_train, "Oversampled ")
# Fitting Simple Linear Regression to the Training set
regressor = LinearRegression()
regressor.fit(X_train, y_train)
# Predicting the Test set results
y_predict = regressor.predict(X_test)
y_pred = np.where(y_predict > 0.5, 1, 0)
evaluate("Linear Regression", y_test, y_pred)
import gsmote.comparison_testing.preprocessing as pp
# Partition the dataset
from sklearn.model_selection import train_test_split
date_file = "../../data/KDD.csv"
X, y = pp.pre_process(date_file)
X, X_t, y, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
# Instantiate a PCA object for the sake of easy visualisation
pca = PCA(n_components=2)
# Fit and transform x to visualise inside a 2D feature space
X_vis = pca.fit_transform(X)
X_resampled, y_resampled = gs.OverSample(X, y)
X_res_vis = pca.transform(X_resampled)
# Two subplots, unpack the axes array immediately
f, (ax1, ax2) = plt.subplots(1, 2)
c0 = ax1.scatter(X_vis[y == '0', 0],
X_vis[y == '0', 1],
label="Class #0",
alpha=0.5,
marker='.')
c1 = ax1.scatter(X_vis[y == '1', 0],
X_vis[y == '1', 1],
label="Class #1",
alpha=0.5,
marker='.')
date_file = "../../data/adultmini.csv".replace('\\', '/')
# date_file = "content/pygsom/data/ecoli.csv".replace('\\', '/')
X, y = pp.preProcess(date_file)
X_t, X_test, y_t, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=0)
# Visualize original data
vs(X_t, y_t, "Original data")
# oversample
print("Oversampling inprogress...")
X_train, y_train = GSMOTE.OverSample(X_t, y_t)
# visualize oversampled data
print("Oversampling completed")
print("Plotting oversampled data...")
vs(X_train, y_train, "Oversampled ")
print("Plotting completed")
def linear_training():
# Fitting Simple Linear Regression to the Training set
regressor = LinearRegression()
regressor.fit(X_train, y_train)
# Predicting the Test set results
y_predict = regressor.predict(X_test)
return class_counter2.most_common(1)[0][0]
if __name__ == '__main__':
np.random.seed(1)
df = pd.read_csv(data_filename)
print(df.shape)
# data_training = df.iloc[:, 1:17]
# gsom = GSOM(.83, 16, max_radius=4)
# gsom.fit(data_training.to_numpy(), 100, 50)
# x= (data_training.to_numpy())
# gsom.predict(df,"Name","label")
X, y = pp.preProcess(data_filename)
X_f, y_f = GSMOTE.OverSample(X, y)
y_f = y_f.astype(int)
y1 = np.copy(y_f)
y = np.column_stack([y1, y_f])
labels = ["Name", "label"]
y = np.vstack((labels, y))
frame = pd.DataFrame(y[1:, :], columns=y[0, :])
gsom1 = GSOM(.83, X_f.shape[1], max_radius=4)
gsom1.fit(X_f[:-10, :], 100, 50)
gsom1.labelling_gsom(X_f[:-10, :], frame.iloc[:-10, :], "Name", "label")
gsom1.finalize_gsom_label()
y_pred = gsom1.predict_values(X_f[-10:, :], frame.iloc[-10:, :])
print(y_pred)
print("complete")