def main():
df_train = pd.read_csv('../train_dataset.csv')
df_test = pd.read_csv('../test_dataset.csv')
X_train, y_train = df_train.iloc[:, 2:], df_train.iloc[:, 0]
X_test, y_test = df_test.iloc[:, 2:], df_test.iloc[:, 0]
unique_labels = sorted(y_train.unique().tolist())
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
print("\n\n{}\n".format(clf.score(X_test, y_test)))
y_predicted = clf.predict(X_test)
print("Generating confusion matrix figure... \n")
stdfunc.plot_confusion_matrix(
y_test,
y_predicted,
ml_name='DT',
classes=unique_labels,
title='Confusion matrix for Decision Tree evaluation')
print("Generating classification report figure... \n")
stdfunc.plot_classification_report(
y_test,
y_predicted,
ml_name='DT',
classes=unique_labels,
title='Classification report for Decision Tree evaluation')
def main():
df_train = pd.read_csv('../train_dataset.csv')
df_test = pd.read_csv('../test_dataset.csv')
X_train, y_train = df_train.iloc[:, 2:], df_train.iloc[:, 0]
X_test, y_test = df_test.iloc[:, 2:], df_test.iloc[:, 0]
unique_labels = sorted(y_train.unique().tolist())
print(X_train)
print(X_test)
# hyper-parameters inferred by running skopt
clf = SVC(C=447.81051228628013, coef0=0.12426850569436687, decision_function_shape="ovr",
degree=2, gamma=0.02413100813767344, kernel="rbf", tol=0.004948161298923479, verbose=True)
clf.fit(X_train, y_train)
print("\n\n{}\n".format(clf.score(X_test, y_test)))
y_predicted = clf.predict(X_test)
print("Generating confusion matrix figure... \n")
stdfunc.plot_confusion_matrix(y_test, y_predicted, ml_name='SVM',
classes=unique_labels,
title='Confusion matrix for SVM evaluation')
print("Generating classification report figure... \n")
stdfunc.plot_classification_report(y_test, y_predicted, ml_name='SVM',
classes=unique_labels,
title='Classification report for SVM evaluation')
def main():
df_train = pd.read_csv('../train_dataset.csv')
df_test = pd.read_csv('../test_dataset.csv')
X_train, y_train = df_train.iloc[:, 2:], df_train.iloc[:, 0]
X_test, y_test = df_test.iloc[:, 2:], df_test.iloc[:, 0]
unique_labels = sorted(y_train.unique().tolist())
# hyper-parameters inferred by running auto-sklearn
clf = GradientBoostingClassifier(learning_rate=0.0433556140045585,
n_estimators=388, subsample=0.8291104221904706, criterion='mse',
min_samples_split=13, min_samples_leaf=15,
max_depth=10, max_features=0.33000096635982235, verbose=True)
# hyper parameters inferred by running hyperopt-sklearn
# clf = GradientBoostingClassifier(criterion="mse", learning_rate=0.28539836866041823, max_depth=9, max_features=0.3842196341383438,
# min_samples_leaf=14, min_samples_split=9, n_estimators=734, subsample=0.7421091918485163)
clf.fit(X_train, y_train)
print("\n\n{}\n".format(clf.score(X_test, y_test)))
y_predicted = clf.predict(X_test)
print("Generating confusion matrix figure... \n")
stdfunc.plot_confusion_matrix(y_test, y_predicted, ml_name='DT',
classes=unique_labels,
title='Confusion matrix for Decision Tree evaluation')
print("Generating classification report figure... \n")
stdfunc.plot_classification_report(y_test, y_predicted, ml_name='DT',
classes=unique_labels,
title='Classification report for Decision Tree evaluation')
def main():
df_train = pd.read_csv('../train_dataset.csv')
df_test = pd.read_csv('../test_dataset.csv')
X_train, y_train = df_train.iloc[:, 2:], df_train.iloc[:, 0]
X_test, y_test = df_test.iloc[:, 2:], df_test.iloc[:, 0]
unique_labels = sorted(y_train.unique().tolist())
clf = GaussianProcessClassifier(max_iter_predict=500, warm_start=True, n_jobs=-1)
clf.fit(X_train, y_train)
print("\n\n{}\n".format(clf.score(X_test, y_test)))
y_predicted = clf.predict(X_test)
print("Generating confusion matrix figure... \n")
stdfunc.plot_confusion_matrix(y_test, y_predicted, ml_name='GP',
classes=unique_labels,
title='Confusion matrix for Gaussian Process evaluation')
print("Generating classification report figure... \n")
stdfunc.plot_classification_report(y_test, y_predicted, ml_name='GP',
classes=unique_labels,
title='Classification report for Gaussian Process evaluation')
def main():
df_train = pd.read_csv('../train_dataset.csv')
df_test = pd.read_csv('../test_dataset.csv')
X_train, y_train = df_train.iloc[:, 2:], df_train.iloc[:, 0]
X_test, y_test = df_test.iloc[:, 2:], df_test.iloc[:, 0]
unique_labels = sorted(y_train.unique().tolist())
# hyper-parameters inferred from running hyperopt-sklearn
clf = RandomForestClassifier(bootstrap=False,
class_weight=None,
criterion='entropy',
max_depth=None,
max_features='sqrt',
max_leaf_nodes=None,
min_impurity_decrease=0.0,
min_impurity_split=None,
min_samples_leaf=1,
min_samples_split=2,
min_weight_fraction_leaf=0.0,
n_estimators=75,
n_jobs=1,
oob_score=False,
random_state=1,
verbose=False,
warm_start=False)
clf.fit(X_train, y_train)
print("\n\n{}\n".format(clf.score(X_test, y_test)))
y_predicted = clf.predict(X_test)
print("Generating confusion matrix figure... \n")
stdfunc.plot_confusion_matrix(
y_test,
y_predicted,
ml_name='RF',
classes=unique_labels,
title='Confusion matrix for Random Forest evaluation')
print("Generating classification report figure... \n")
stdfunc.plot_classification_report(
y_test,
y_predicted,
ml_name='RF',
classes=unique_labels,
title='Classification report for Random Forest evaluation')
def main():
df_train = pd.read_csv('../train_dataset.csv')
df_test = pd.read_csv('../test_dataset.csv')
X_train, y_train = df_train.iloc[:, 2:].values, df_train.iloc[:, 0].values
X_test, y_test = df_test.iloc[:, 2:].values, df_test.iloc[:, 0].values
unique_labels = sorted(set(y_train.tolist()))
le = preprocessing.LabelEncoder()
le.fit(y_train)
y_train = le.transform(y_train)
y_test = le.transform(y_test)
# hyper-parameters inferred by running hyperopt-sklearn
clf = XGBClassifier(colsample_bylevel=0.8737745469231419,
colsample_bytree=1.0,
gamma=4.858229599937319e-07,
learning_rate=0.4853267733199465,
max_delta_step=0,
max_depth=9,
min_child_weight=0,
n_estimators=64,
reg_alpha=2.5693931492543614e-05,
reg_lambda=6.027978487395207e-05,
scale_pos_weight=73.0915750362818,
subsample=0.5410531887103683)
clf.fit(X_train, y_train)
print("\n\n{}\n".format(clf.score(X_test, y_test)))
y_predicted = clf.predict(X_test)
print("Generating confusion matrix figure... \n")
stdfunc.plot_confusion_matrix(
y_test,
y_predicted,
ml_name='XG',
classes=unique_labels,
title='Confusion matrix for XGBoost evaluation')
print("Generating classification report figure... \n")
stdfunc.plot_classification_report(
y_test,
y_predicted,
ml_name='XG',
classes=unique_labels,
title='Classification report for XGBoost evaluation')
def main():
df_train = pd.read_csv('../train_dataset.csv')
df_test = pd.read_csv('../test_dataset.csv')
X_train, y_train = df_train.iloc[:, 2:], df_train.iloc[:, 0]
X_test, y_test = df_test.iloc[:, 2:], df_test.iloc[:, 0]
unique_labels = sorted(y_train.unique().tolist())
curr_pred, curr_score = None, 0
for k in range(1, 20):
clf = KNeighborsClassifier(n_neighbors=k, n_jobs=-1)
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
y_predicted = clf.predict(X_test)
if score > curr_score:
print("K = {} -- {}".format(k, score))
curr_pred = y_predicted
curr_score = score
print("Generating confusion matrix figure... \n")
stdfunc.plot_confusion_matrix(
y_test,
curr_pred,
ml_name='Nearest_Neighbor',
classes=unique_labels,
title='Confusion matrix for Nearest Neighbor evaluation')
print("Generating classification report figure... \n")
stdfunc.plot_classification_report(
y_test,
curr_pred,
ml_name='Nearest_Neighbor',
classes=unique_labels,
title='Classification report for Nearest Neighbor evaluation')