tokenizer = None
label_encoder = None
encoded_labels = None
inputdata = None
test_df = None
text_X = None
test_Y = None
shaper = None
model = None
from reader import Reader
from dataloader import Utils
from dataloader import DataSet
from model import ModelBuilder
from writer import Writer
if __name__ == "__main__" :
df = Reader.read_csv("data","sentiment_train.csv",config="default",streamType="csv",columns="0,1",filter="full",count=5)
tokenizer = Utils.get_text_tokenizer(df,1)
label_encoder = Utils.get_label_encoder(df,0)
encoded_labels = DataSet.get_encodered_labels(df,0,label_encoder)
inputdata = DataSet.text_to_matrix(df,1,tokenizer)
test_df = Reader.read_csv("data","sentiment_test.csv",config="default",streamType="df",columns="0,1",filter="full",count=5)
text_X = DataSet.text_to_matrix(test_df,1,tokenizer)
test_Y = DataSet.get_encodered_labels(test_df,0,label_encoder)
shaper = tuple([inputdata, encoded_labels, text_X, test_Y])
model = ModelBuilder.train_model((ModelBuilder.create_model('KNN Classifier',shape='2,2',config='{"n_neighbors":1,"algorithm":"ball_tree","weights":"distance"}')),shaper,'true')
Writer.write_csv((DataSet.get_label((ModelBuilder.predict_model(model,text_X)),0,label_encoder)),"default")
config="default",
streamType="csv",
columns="0,1",
filter="full",
count=5,
header="1",
transformers=None)
tokenizer = Utils.get_text_tokenizer(df, 1)
label_encoder = Utils.get_label_encoder(df, 0)
encoded_labels = DataSet.get_encodered_labels(df, 0, label_encoder)
inputdata = DataSet.text_to_matrix(df, 1, tokenizer)
modeldef = ModelBuilder.create_model(
'Keras Sequential Model',
shape='2,2',
config=
('{"loss_function":"categorical_crossentropy","optimizer":"adam"}', [
'{ "layer_type":"Dense" ,"activation":"relu","optimizer":"Adam","threshold":"512","input_shape":"10000,"}',
'{ "layer_type":"Dropout" ,"activation":"relu","optimizer":"Adam","threshold":".5","input_shape":""}',
'{ "layer_type":"Dense" ,"activation":"softmax","optimizer":"Adam","threshold":"4","input_shape":""}'
]))
test_df = Reader.read_csv("data",
"sentiment_test.csv",
config="default",
streamType="df",
columns="0,1",
filter="full",
count=5,
header="1",
transformers=None)
text_X = DataSet.text_to_matrix(test_df, 1, tokenizer)
test_Y = DataSet.get_encodered_labels(test_df, 0, label_encoder)
df = Reader.read_csv("data",
"NSE_Abbott India Limited.csv",
config="default",
streamType="csv",
columns="",
filter="full",
count=5,
header="1",
transformers=None)
shaper = DataSet.shape_data_frame(df,
'',
x_columns='1:9',
y_columns='3',
x_dimention='3',
y_dimention='1',
y_offset=1,
test_data_size=20)
normalizer = Utils.get_preprocessing_scaler(min_max_tuple=(-1, 1))
shaper = Utils.fit_transform(shaper, normalizer)
model_def = ModelBuilder.create_model(
'Keras Sequential Model',
shape='2,2',
config=('{"loss_function":"mean_absolute_error","optimizer":"adam"}', [
'{ "layer_type":"LSTM" ,"activation":"tanh","optimizer":"Adam","threshold":"100","input_shape":"1,8"}',
'{ "layer_type":"Dropout" ,"activation":"sigmoid","optimizer":"sgd","threshold":"0.2","input_shape":""}',
'{ "layer_type":"Dense" ,"activation":"linear","optimizer":"Adam","threshold":"1","input_shape":""}'
]))
model = ModelBuilder.train_model(model_def, shaper, 'true')
result = ModelBuilder.predict_model(model, shaper)
result = Utils.inverse_transform(result, normalizer, axis='y')
print(result)
df = Reader.read_csv("data",
"NSE_Abbott India Limited.csv",
config="default",
streamType="csv",
columns="")
shaper = DataSet.shape_data_frame(df,
'',
x_columns='1:9',
y_columns='3',
x_dimention='2',
y_dimention='2',
y_offset=1,
test_data_size=20)
normalizer = Utils.get_preprocessing_scaler(min_max_tuple=(-1, 1))
shaper = Utils.fit_transform(shaper, normalizer)
print(shaper[0].shape)
print(shaper[2].shape)
print(shaper[1].shape)
print(shaper[3].shape)
model_def = ModelBuilder.create_model('Gradient Boosting Regressor',
shape='2,2',
config='{"random_state":0}')
model = ModelBuilder.train_model(model_def, shaper, 'true')
result = ModelBuilder.predict_model(model, shaper)
result = Utils.inverse_transform(result, normalizer)
print(result)