def main(targets):
'''
Runs the main project pipeline logic, given the targets.
targets must contain: 'data', 'analysis', 'model'.
`main` runs the targets in order of data=>analysis=>model.
'''
start_prog = timeit.default_timer()
if 'data' in targets:
with open('config/data-params.json', 'r', encoding="utf-8") as fh:
data_cfg = json.load(fh)
# make the data target
data = clean_data(**data_cfg)
if 'analysis' in targets:
with (open('config/analysis-params.json')) as fh:
analysis_cfg = json.load(fh)
#make the data target
X, y = prepare_data(data, **analysis_cfg)
if 'model' in targets:
with open('config/model-params.json') as fh:
model_cfg = json.load(fh)
# make the data target
train_data(X, y, **model_cfg)
stop_prog = timeit.default_timer()
print("overall runtime: ", stop_prog - start_prog)
return
def train():
path = 'models/'
if len(os.listdir(path)) == 0:
train_data(log_writer)
else:
pass
return render_template('index.html')
def __init__(self, load):
self.lastPercent = 0.0
self.bestPercent = 0.0
if (load != '0'):
print("\ncreating train data...")
sys.stdout.flush()
self.td = train.train_data(files_location)
pickle.dump(self.td, open("_train_data.p", "wb"))
print("created sucessfully\n")
sys.stdout.flush()
else:
print("\nloading train data...")
sys.stdout.flush()
self.td = pickle.load(open("_train_data.p", "rb"))
print("loaded sucessfully\n")
sys.stdout.flush()
self.nn = nn_matrix.neural_network(len(self.td.inputs[0][0]),len(self.td.authors),nlayers,dummy_var, learn_rate)
def train():
print('train start')
data_dir=request.args.get('data_dir')
train_dir=request.args.get('train_dir')
train_dir=makeDir(train_dir)
if train_data(data_dir=data_dir,train_dir=train_dir):
json_path=os.path.join(data_dir,'state.json')
json_state={"names":[]}
filenames=os.listdir(data_dir)
for filename in filenames:
extension = os.path.splitext(filename)[1][1:].strip()
if extension=='bin':
json_temp={"name":filename}
json_state['names'].append(json_temp)
with open(json_path,"w") as outfile :
json.dump(json_state,outfile)
print(json_state)
print('train end')
return 'true'
def __init__(self):
self.there_is_a_winner = False
self.g = ludopy.Game()
self.player = None
self.Q = []
self.ca = capture_image()
self.list_winner = []
self.number_winner_my_player = 0
self.tr = train_data()
self.player_last_piece = []
self.second_player = 0
self.file_name = ""
self.file_plyer_hist = ""
self.type_play = True
self.winner = 0
self.my_player_winner = False
self.gamma_m = 0
self.alfa_m = 0
self.percentage = []
self.epsilon = 0
def summary():
print("summary")
train_data()
test_data()
ans_data()
print("train2emb模型运行完成")
from train import train
from predict import predict_data
from train import train_data
import numpy as np
import pandas as pd
#from lightgbm import LGBMClassifier
#est_bin是做了每个特征dbscan分箱
#train_x,train_y,est_kbin = train_data()
train_x, train_y = train_data()
train_x.drop(
[
'lat_var_skew',
'lon_var_skew',
'velocity_var_skew',
'velocity_var_covar',
'angle_var_mean',
'computed_angle_var_mean',
'computed_angle_var_skew',
'computed_angle_var_covar',
#'angle_var_velocity_cov'
],
axis=1,
inplace=True)
#构建测试集数据
#test_x,test_id = predict_data(est_kbin)
test_x, test_id = predict_data()
test_x.drop(
[
'lat_var_skew',
'lon_var_skew',
#!/usr/bin/env python3 -W ignore::DeprecationWarning
import sys
import warnings
from fetch import fetch_data
from train import train_data
# suppress all warnings
warnings.filterwarnings("ignore")
if __name__ == "__main__":
fetch_obj = fetch_data(data_type=0)
test_obj = fetch_data(data_type=1)
train_obj = train_data(fetch_obj.label_df, fetch_obj.pseudo_df,
test_obj.unlabel_df)
# apply a tf-idf model with SVD
combine_data = [*train_obj.labeled_data, *train_obj.pseudo_data]
train_obj.fit_vectorizer(combine_data,
min_df=0.010,
max_df=0.8,
ngram_range=(1, 2),
svd=True)
# using lda
train_obj.train_model()
# test data
train_obj.fit_vectorizer(train_obj.test_data,
min_df=0.010,
max_df=0.8,
ngram_range=(1, 2),
svd=True,
def train():
train_data()
return render_template('index.html')
def train():
train_data(log_writer)
return render_template('index.html')
def train():
train_data(log_writer)
return render_template('results.html')
def capture():
t = train_data()
t.record()
line = ' '.join(string_formatter)
fp.write(line)
fp.write(linesep)
fp.close()
if mode == "train":
if len(argv) != 5:
print(
"USAGE: python topics.py mode dataset-directory model-file [fraction]"
)
exit(1)
fraction = float(argv[4])
print("Training started.")
print("Please wait as it could take a while to create model...")
model = train.train_data(dataset_dir, fraction)
write_top_words_to_file(model, "distinctive_words.txt")
print("Top 10 words at each topic is written into distinctive_words.txt.")
serialize_model(model, model_file)
print("Model File created")
exit(0)
if mode == "test":
model = deserialize_model(model_file)
print("Model loaded successfully.")
result = test.test_data(model, dataset_dir)
print(result)
exit(0)
print("Operation not supported")
exit(1)