def train(n_queries=10, mode='boreholes'):
datafile = paths.get_dataset_path(name, mode)
df = pd.read_csv(datafile)
df = df.loc[df['Content'] != '[]']
clf = Pipeline(
[
('list2str', FunctionTransformer(concat_tables)),
#('vect', CountVectorizer(ngram_range=(1, 2), min_df=0.01)),
('tfidf', TfidfVectorizer(ngram_range=(1, 2), min_df=0.0025)
), # min_df discourages overfitting
('cnb', ComplementNB(alpha=0.2))
],
verbose=True)
accuracy, learner = active_learning.train(df,
y_column,
n_queries,
clf,
datafile,
limit_cols=limit_cols,
mode=mode)
model_loc = paths.get_model_path(name, mode)
with open(model_loc, "wb") as file:
pickle.dump(learner, file)
return learner
def train(
n_queries=10,
mode=paths.dataset_version,
spec_name=name
): #datafile=settings.get_dataset_path('heading_id_intext'), model_file=settings.get_model_path('heading_id_intext'),
datafile = paths.get_dataset_path(name, mode)
model_file = paths.get_model_path(spec_name, mode)
data = pd.read_csv(datafile)
if 'no_toc' in model_file:
limit_cols.extend(['MatchesHeading', 'MatchesType'])
estimator = Pipeline(
[
(
'text',
ColumnTransformer(
[(
'cnb', Text2CNBPrediction(), 1
) # 1 HAS TO BE 'TEXT'. changing it to int bc AL uses np arrays
],
remainder="passthrough")),
('forest', RandomForestClassifier())
],
verbose=True)
accuracy, learner = active_learning.train(data, y_column, n_queries,
estimator, datafile, limit_cols)
print(accuracy)
with open(model_file, "wb") as file:
pickle.dump(learner, file)
print("End of training stage. Re-run to train again")
def train(datafile=paths.get_dataset_path(name),
model_file=paths.get_model_path(name)
): #settings.heading_classification_model_file):
data = pd.read_csv(datafile)
X, Y = data_prep(data, y=True)
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.20)
clf = Pipeline([
('tfidf', TfidfVectorizer(
analyzer='word',
ngram_range=(1, 2))), #(token_pattern=r'([a-zA-Z]|[0-9])+')),
('clf', ComplementNB(norm=True))
])
clf = clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
#weights = eli5.formatters.as_dataframe.explain_weights_df(clf, feature_names=clf['tfidf'].get_feature_names(), top=10, target_names=y_test)
#print(weights)
#prediction = eli5.formatters.as_dataframe.explain_prediction_df(clf, X_test[0], feature_names=clf['tfidf'].get_feature_names(), target_names=y_test)
#print(prediction)
accuracy = accuracy_score(y_test, y_pred)
print(accuracy)
report = classification_report(Y, clf.predict(X))
print(report)
with open(paths.result_path + name + '_CNB_report.txt', "w") as r:
r.write(report)
with open(model_file, "wb") as file:
pickle.dump(clf, file)
def run_model(model_name, model_type='NN', mode=paths.dataset_version):
nn = NeuralNetwork(model_name, model_type)
data = pd.Series(['page 3 of 8',
'bhp hello 3',
'epm3424 \t3 \tfebruary 1900',
'epm3424 \tpage 3 \tfebruary 1900',
'epm3424 page \t3 \tfebruary 1900',
'epm3424 page 3 \tfebruary 1900',
'epm34985 \t40',
'8 \t9 \t10',
'8 may 1998 \treport 90',
'3 \tbhp annual report'])
#trans_data = data.apply(lambda x: transform_text(x, transform_all=False))
r = nn.predict(data)
print(r)
all_predictions = False
if all_predictions:
df = pd.read_csv(paths.get_model_path(name, mode))
#df = pd.read_csv(paths.page_extraction_dataset)
data = df.transformed
r = nn.predict(data)
correct = 0
incorrect = 0
for i, row in df.iterrows():
print(row.original, ', ', r[i])
if str(row.pagenum) != r[i]:
incorrect += 1
else:
correct += 1
print('real accuracy: ', correct/(correct+incorrect))
def train(n_queries=10, mode=paths.dataset_version): #, model='forest') datafile=data_path,
datafile = paths.get_dataset_path(name, mode) # need to define these here because mode may be production
model_path = paths.get_model_path(name, mode)
data = pd.read_csv(datafile)
accuracy, learner = active_learning.train(data, y_column, n_queries, estimator, datafile, limit_cols=limit_cols)
with open(model_path, "wb") as file:
pickle.dump(learner, file)
print("End of training stage. Re-run to train again")
return accuracy
def predict(inputs, mode=mode):
if isinstance(inputs, str):
inputs = [inputs]
with open(paths.get_model_path(name, mode), "rb") as file:
#with open(paths.heading_classification_model_file, "rb") as file:
model = pickle.load(file)
pred = model.predict(inputs)
proba = model.predict_proba(inputs)
return pred, proba #, model
def train_models_pt2():
heading_id_toc_nn = heading_id_toc.NeuralNetwork()
heading_id_toc_nn.train()
# page_id_nn = page_identification.NeuralNetwork()
# page_id_nn.train()
heading_id_intext.train()
heading_id_intext.train(
model_file=paths.get_model_path('heading_id_intext_no_toc'))
def create_dataset(mode=paths.dataset_version):
sourcefile = paths.get_model_path(name, mode)
texts = pd.read_csv(sourcefile)
page_texts = texts.loc[texts.tag == 1]
#page_texts.transformed = page_texts.original.apply(lambda x: transform_text(x, transform_all=False))
page_texts = page_texts.drop(['tag'], axis=1)
page_texts['pagenum'] = None
#page_texts.to_csv(settings.page_extraction_dataset, index=False)
return page_texts
def run_model(mode=paths.production):
nn = NeuralNetwork()
model_loc = paths.get_model_path(name, mode=mode)
nn.load_model_from_file(model_loc=model_loc)
df = pd.read_csv(paths.get_dataset_path(name, mode=mode), usecols=['original'])
#df = pd.read_csv(paths.marginals_id_trans_dataset, usecols=['original'])
#data = df.original
data = pd.Series(['page 8', 'bhp hello 3', '12 month report', 'epm3424 3 february 1900',
'epm23 february 2000', 'epm34985 4000'])
p, r = nn.predict(data)#.original)
for i, row in df.iterrows():
print(row.original, ', ', p[i], ', ', r[i])
def classify(data, model_name, y_column, limit_cols, mode=paths.dataset_version):
#frame = inspect.stack()[9] # 9 only works if this functions is called from get_classified # 1 if called from model file
model_path = paths.get_model_path(model_name, mode)
if not os.path.exists(model_path):
frame = inspect.stack()[2] # 0: this, 1: mlh.get_classified, 2: model file
module = inspect.getmodule(frame[0]) # inspect.getmodule(frame[0]) # gets the module that this function was called from to call the correct training function
module.train(n_queries=0, mode=mode, spec_name=model_name) #datafile=settings.get_dataset_path(model_name, mode), model_file=model_path)
with open(model_path, "rb") as file:
model = joblib.load(file)
if isinstance(data, pd.DataFrame) and y_column in data.columns:
limit_cols.append(y_column) #better than passing y_column to data prep to be removed because then y will also be returned
data = data_prep(data, limit_cols)
pred = model.predict(data)
proba = model.predict_proba(data)
#print(proba)
return pred, proba
def train(n_queries=10, mode=paths.dataset_version): #datafile=data_path, ):
datafile = paths.get_dataset_path(name, mode)
data = pd.read_csv(datafile)
accuracy, learner = active_learning.train(data,
y_column,
n_queries,
estimator,
datafile,
mode=mode)
if type(learner) == tree._classes.DecisionTreeClassifier:
tree.plot_tree(learner, feature_names=include_cols, class_names=True)
plt.show()
with open(paths.get_model_path(name, mode), "wb") as file:
pickle.dump(learner, file)
print("End of training stage. Re-run to train again")
return accuracy
def train(
n_queries=10,
mode=paths.dataset_version
): # datafile=settings.get_dataset_path(name), model_file=settings.get_model_path(name),
datafile = paths.get_dataset_path(name, mode)
if not os.path.exists(datafile):
data = create_dataset()
data.to_csv(datafile, index=False)
else:
data = pd.read_csv(datafile)
clf = RandomForestClassifier() #tree.DecisionTreeClassifier()
accuracy, clf = al.train(data, y_column, n_queries, clf, datafile,
limited_cols)
print(accuracy)
model_file = paths.get_model_path(name, mode)
with open(model_file, "wb") as file:
pickle.dump(clf, file)
def train(self, n_queries=10, mode=paths.dataset_version): #settings.marginals_id_trans_dataset):
file = paths.get_dataset_path(name, mode)
df = pd.read_csv(file)
#self.X = df['transformed']
#self.Y = df['tag']
self.max_words, self.max_len = check_maxlens(df)
lstm = KerasClassifier(build_fn=self.LSTM, batch_size=self.batch_size, epochs=self.epochs,
validation_split=0.2)
estimator = Pipeline([
#('transform1', ColumnTransformer([
('transform_text', FunctionTransformer(transform_text_wrapper)),# 0)
#], remainder="passthrough")),
('transform2', Text2Seq(classes=2)),
('lstm', lstm)
], verbose=True)
accuracy, learner = active_learning.train(df, y_column, n_queries, estimator, file, limit_cols=limit_cols)
self.model = learner
# self.tok = Tokenizer(num_words=self.max_words+1) # only num_words-1 will be taken into account!
# self.model = self.LSTM()
#
# X_train, X_test, Y_train, Y_test = train_test_split(self.X, self.Y, test_size=0.15)
#
# self.tok.fit_on_texts(X_train)
# sequences = self.tok.texts_to_sequences(X_train)
# sequences_matrix = sequence.pad_sequences(sequences, maxlen=self.max_len)
# y_binary = to_categorical(Y_train)
# self.model.summary()
# self.model.fit(sequences_matrix, y_binary, batch_size=self.batch_size, epochs=self.epochs,
# validation_split=0.2) #, callbacks=[EarlyStopping(monitor='val_loss',min_delta=0.0001)]
#
# test_sequences = self.tok.texts_to_sequences(X_test)
# test_sequences_matrix = sequence.pad_sequences(test_sequences, maxlen=self.max_len)
#
# accr = self.model.evaluate(test_sequences_matrix, to_categorical(Y_test))
# print('Test set\n Loss: {:0.3f}\n Accuracy: {:0.3f}'.format(accr[0], accr[1]))
self.model_loc = paths.get_model_path(name, mode)
#self.model.save(self.model_loc)
#joblib.dump(self.tok, self.tok_loc)
with open(self.model_loc, "wb") as f:
pickle.dump(self.model, f)
from sklearn import ensemble
import pickle
import re
from report import active_learning, machine_learning_helper as mlh
name = 'marginal_lines'
y_column = 'Marginal'
columns = ['DocID', 'PageNum', 'LineNum', 'NormedLineNum','Text', 'Words2Width', 'WordsWidth', 'Width', 'Height',
'Left', 'Top', 'ContainsNum', 'ContainsTab', 'ContainsPage', 'Centrality', y_column, 'TagMethod']
limit_cols=['DocID', 'Text', 'LineNum']
include_cols = ['PageNum', 'NormedLineNum', 'Words2Width', 'WordsWidth', 'Width', 'Height', 'Left', 'Top',
'ContainsNum', 'ContainsTab', 'ContainsPage', 'Centrality']
estimator = ensemble.RandomForestClassifier()
data_path = paths.get_dataset_path(name)
model_path = paths.get_model_path(name)
def contains_num(string):
if re.search(r'(\s|^)[0-9]+(\s|$)', string):
return 1
return 0
def contains_tab(string):
if re.search(r'\t', string):
return 1
return 0
def contains_page(string):
def train(self, n_queries=10, mode=paths.dataset_version): #settings.page_extraction_dataset):
file = paths.get_dataset_path(name, mode)
df = pd.read_csv(file)
#self.X = df['transformed']
#self.X = df['transformed'] # self.X only exists here to get proper maxlens
self.Y = df['position'] # try with y position instead of y value
#transform = FunctionTransformer(lambda x: num2word(x)) # not sure this will work
#self.X = self.X.apply(lambda x: num2word(x))
#self.max_words, self.max_len = check_maxlens(self.X)
self.max_len = 20 # assuming max num of words in line will be 20
self.classes, y_vectorised = self.position2int()
self.inv_classes = {v: k for k, v in self.classes.items()}
y_masked = np.zeros((self.Y.size, self.max_len))
for i, j in zip(y_masked, y_vectorised):
p = self.inv_classes[j]
i[p] = 1
self.num_classes = len(self.classes.items())
nn = KerasClassifier(build_fn=self.NN, batch_size=self.batch_size, epochs=self.epochs, validation_split=0.2)
clf = Pipeline([
('transform_text', FunctionTransformer(transform_text_wrapper)),
#('num2word', FunctionTransformer(lambda x: num2word(x))),
('transform', Text2Seq(classes=self.num_classes, pad_len=self.max_len)),
('nn', nn)
], verbose=True)
accuracy, learner = active_learning.train(df, y_column, n_queries, clf, file, limit_cols=limit_cols)
self.model = learner
self.model_loc = paths.get_model_path(name, mode)
# self.tok = Tokenizer(num_words=self.max_words+1) # only num_words-1 will be taken into account!
# if self.mode_type == 'LSTM':
# self.model = self.LSTM()
# else:
# self.model = self.NN()
#
# X_train, X_test, Y_train, Y_test = train_test_split(self.X, y_masked, test_size=0.15)
#
# self.tok.fit_on_texts(self.X)
# sequences = self.tok.texts_to_sequences(X_train)
# sequences_matrix = sequence.pad_sequences(sequences, maxlen=self.max_len)
# #y_binary = to_categorical(Y_train) # y needs to be onehot encoded
#
# self.model.summary()
# self.model.fit(sequences_matrix, Y_train, batch_size=self.batch_size, epochs=self.epochs,
# validation_split=0.2) #, callbacks=[EarlyStopping(monitor='val_loss',min_delta=0.0001)]
#
# test_sequences = self.tok.texts_to_sequences(X_test)
# test_sequences_matrix = sequence.pad_sequences(test_sequences, maxlen=self.max_len)
#
# accr = self.model.evaluate(test_sequences_matrix, Y_test)
# print('Test set\n Loss: {:0.3f}\n Accuracy: {:0.3f}'.format(accr[0], accr[1]))
#self.model.save(self.model_loc)
with open(self.model_loc, "wb") as f:
pickle.dump(self.model, f)
self.classes_loc = paths.get_model_path(name, mode, classes=True) #self.model_path + self.model_name + 'class_dict.joblib'
#joblib.dump(self.tok, self.tok_loc)
joblib.dump(self.inv_classes, self.classes_loc)
print("End of training stage. Re-run to train again")
return accuracy
