print(len(feat), 25)
GloveDimOption = '50' # this could be 50 (171.4 MB), 100 (347.1 MB), 200 (693.4 MB), or 300 (1 GB)
embeddings_index = loadGloveModel('data/glove.6B.' + GloveDimOption + 'd.txt')
# print(embeddings_index['apple'])
# print(embeddings_index['mango'])
embeddings_index[''] = np.zeros(50)
embeddings_index['*root'] = np.ones(50)
enc = CategoricalEncoder(encoding='onehot')
X_pos = [['ADJ'], ['ADP'], ['ADV'], ['AUX'], ['CCONJ'], ['DET'], ['INTJ'],
['NOUN'], ['NUM'], ['PART'], ['PRON'], ['PROPN'], ['PUNCT'],
['SCONJ'], ['SYM'], ['VERB'], ['X']]
enc.fit(X_pos)
for i in X_pos:
embeddings_index[i[0]] = pad_sequences(enc.transform([[i[0]]]).toarray(),
maxlen=50,
padding='post')[0]
#embeddings_index[i[0]] = pad_sequences(enc.transform([[i[0]]]).toarray(), maxlen=18, padding='post')[0]
# print(embeddings_index[i[0]])
# print(embeddings_index['apple'])
feat_vect, transit_vect = [], []
# feat_vect = np.array(())
# transit_vect = np.array(())
for i in feat:
#print(i)
sd = np.array(())
X_categorical = X[:, :idx_end_categorical + 1]
# Select only the numerical columns of X (including ft_embedding if present)
X_numerical = X[:, idx_end_categorical + 1:]
return X_categorical, X_numerical
else:
return np.zeros((X.shape[0], 0)), X
if __name__ == "__main__":
df_train = load_and_preprocess('TrainingSet(3).csv', nrows=10000)
# print(df_train.combined_str)
# X = pd.concat([df_train[colnames_categ], df_inference[colnames_categ]])
X = df_train[colnames_categ]
X = X.apply(preprocess_categ_series)
enc = CategoricalEncoder(handle_unknown='ignore')
enc.fit(X)
len_onehot = enc.transform(
df_train[colnames_categ].iloc[:1]).toarray().shape[1]
print(len_onehot)
# train_X_onehot = enc.transform(df_train[colnames_categ]).toarray()
# # inference_X_onehot = enc.transform(df_train[colnames_categ]).toarray()
# print(train_X_onehot.shape)
# print(train_X_onehot[0])
# pprint(enc.categories_)
rt = RandomTreesEmbedding(max_depth=3,
n_estimators=n_estimator,
random_state=0)
rt_lm = LogisticRegression()
pipeline = make_pipeline(rt, rt_lm)
pipeline.fit(X_train, y_train)
y_pred_rt = pipeline.predict_proba(X_test)[:, 1]
fpr_rt_lm, tpr_rt_lm, _ = roc_curve(y_test, y_pred_rt)
# Supervised transformation based on random forests
rf = RandomForestClassifier(max_depth=3, n_estimators=n_estimator)
rf_enc = CategoricalEncoder()
rf_lm = LogisticRegression()
rf.fit(X_train, y_train)
rf_enc.fit(rf.apply(X_train))
rf_lm.fit(rf_enc.transform(rf.apply(X_train_lr)), y_train_lr)
y_pred_rf_lm = rf_lm.predict_proba(rf_enc.transform(rf.apply(X_test)))[:, 1]
fpr_rf_lm, tpr_rf_lm, _ = roc_curve(y_test, y_pred_rf_lm)
grd = GradientBoostingClassifier(n_estimators=n_estimator)
grd_enc = CategoricalEncoder()
grd_lm = LogisticRegression()
grd.fit(X_train, y_train)
grd_enc.fit(grd.apply(X_train)[:, :, 0])
grd_lm.fit(grd_enc.transform(grd.apply(X_train_lr)[:, :, 0]), y_train_lr)
y_pred_grd_lm = grd_lm.predict_proba(
grd_enc.transform(grd.apply(X_test)[:, :, 0]))[:, 1]
fpr_grd_lm, tpr_grd_lm, _ = roc_curve(y_test, y_pred_grd_lm)
# Unsupervised transformation based on totally random trees
rt = RandomTreesEmbedding(max_depth=3, n_estimators=n_estimator,
random_state=0)
rt_lm = LogisticRegression()
pipeline = make_pipeline(rt, rt_lm)
pipeline.fit(X_train, y_train)
y_pred_rt = pipeline.predict_proba(X_test)[:, 1]
fpr_rt_lm, tpr_rt_lm, _ = roc_curve(y_test, y_pred_rt)
# Supervised transformation based on random forests
rf = RandomForestClassifier(max_depth=3, n_estimators=n_estimator)
rf_enc = CategoricalEncoder()
rf_lm = LogisticRegression()
rf.fit(X_train, y_train)
rf_enc.fit(rf.apply(X_train))
rf_lm.fit(rf_enc.transform(rf.apply(X_train_lr)), y_train_lr)
y_pred_rf_lm = rf_lm.predict_proba(rf_enc.transform(rf.apply(X_test)))[:, 1]
fpr_rf_lm, tpr_rf_lm, _ = roc_curve(y_test, y_pred_rf_lm)
grd = GradientBoostingClassifier(n_estimators=n_estimator)
grd_enc = CategoricalEncoder()
grd_lm = LogisticRegression()
grd.fit(X_train, y_train)
grd_enc.fit(grd.apply(X_train)[:, :, 0])
grd_lm.fit(grd_enc.transform(grd.apply(X_train_lr)[:, :, 0]), y_train_lr)
y_pred_grd_lm = grd_lm.predict_proba(
grd_enc.transform(grd.apply(X_test)[:, :, 0]))[:, 1]
fpr_grd_lm, tpr_grd_lm, _ = roc_curve(y_test, y_pred_grd_lm)