def startjob(
csv_file_path=r'C:\Users\57855\Desktop\2%test.csv', #训练文件的路径
model_file=r'C:\Users\57855\Desktop\2%.yaml', #模型配置文件路径
test_file=r'C:\Users\57855\Desktop\2%test_data.csv'): #结果输出路径
#Lugwig教程上的代码
with open(model_file, encoding='utf-8', mode='r') as file:
model_definition = yaml.load(file.read())
print(model_definition)
ludwig_model = LudwigModel(model_definition)
train_stats = ludwig_model.train(csv_file_path,
logging_level=logging_DEBUG)
print(train_stats)
predictions = ludwig_model.predict(test_file,
logging_level=logging_DEBUG)
print(predictions)
ludwig_model.close()
def train(self):
training_dataframe, model_definition = self._create_ludwig_dataframe(
'train')
if self.transaction.lmd['model_order_by'] is None:
timeseries_cols = []
else:
timeseries_cols = list(
map(lambda x: x[0], self.transaction.lmd['model_order_by']))
if len(timeseries_cols) > 0:
training_dataframe, model_definition = self._translate_df_to_timeseries_format(
training_dataframe, model_definition, timeseries_cols, 'train')
with disable_ludwig_output():
model = LudwigModel(model_definition)
# <---- Ludwig currently broken, since mode can't be initialized without train_set_metadata and train_set_metadata can't be obtained without running train... see this issue for any updates on the matter: https://github.com/uber/ludwig/issues/295
#model.initialize_model(train_set_metadata={})
#train_stats = model.train_online(data_df=training_dataframe) # ??Where to add model_name?? ----> model_name=self.transaction.lmd['name']
if self.transaction.lmd['rebuild_model'] is True:
train_stats = model.train(
data_df=training_dataframe,
model_name=self.transaction.lmd['name'],
skip_save_model=True)
else:
model = LudwigModel.load(
self.transaction.lmd['ludwig_data']['ludwig_save_path'])
train_stats = model.train(
data_df=training_dataframe,
model_name=self.transaction.lmd['name'],
skip_save_model=True)
#,model_load_path=self.transaction.lmd['ludwig_data']['ludwig_save_path'])
for k in train_stats['train']:
if k not in self.transaction.lmd['model_accuracy']['train']:
self.transaction.lmd['model_accuracy']['train'][k] = []
self.transaction.lmd['model_accuracy']['test'][k] = []
elif k is not 'combined':
# We should be adding the accuracy here but we only have it for combined, so, for now use that, will only affect multi-output scenarios anyway
pass
else:
self.transaction.lmd['model_accuracy']['train'][k].extend(
train_stats['train'][k]['accuracy'])
self.transaction.lmd['model_accuracy']['test'][k].extend(
train_stats['test'][k]['accuracy'])
'''
@ TRAIN ONLINE BIT That's not working
model = LudwigModel.load(self.transaction.lmd['ludwig_data']['ludwig_save_path'])
for i in range(0,100):
train_stats = model.train_online(data_df=training_dataframe)
# The resulting train_stats are "None"... wonderful -_-
'''
ludwig_model_savepath = Config.LOCALSTORE_PATH.rstrip(
'local_jsondb_store') + self.transaction.lmd['name']
model.save(ludwig_model_savepath)
model.close()
self.transaction.lmd['ludwig_data'] = {
'ludwig_save_path': ludwig_model_savepath
}
self.transaction.hmd['ludwig_data'] = {
'model_definition': model_definition
}
from ludwig import LudwigModel
import pandas as pd
df = pd.read_csv('Tweets.csv')
print(df.head())
model_definition = {
'input_features':[
{'name':'text', 'type':'text'},
],
'output_features': [
{'name': 'airline_sentiment', 'type': 'category'}
]
}
print('creating model')
model = LudwigModel(model_definition)
print('training model')
train_stats = model.train(data_df=df)
model.close()