def load_model():
print("**************Please wait....Loading weights*********************")
global ludwig_model
model_definition = get_model_definition()
ludwig_model = LudwigModel(model_definition)
train_model()
ludwig_model.load(MODEL_PATH)
print("weights loaded")
def predict(self, mode='predict', ignore_columns=[]):
predict_dataframe, model_definition = self._create_ludwig_dataframe(
mode)
model_definition = self.transaction.hmd['ludwig_data'][
'model_definition']
model = LudwigModel.load(
self.transaction.lmd['ludwig_data']['ludwig_save_path'])
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:
predict_dataframe, model_definition = self._translate_df_to_timeseries_format(
predict_dataframe, model_definition, timeseries_cols)
for ignore_col in ignore_columns:
try:
predict_dataframe[ignore_col] = [None] * len(
predict_dataframe[ignore_col])
except:
for date_appendage in ['_year', '_month', '_day']:
predict_dataframe[ignore_col + date_appendage] = [
None
] * len(predict_dataframe[ignore_col + date_appendage])
with disable_ludwig_output():
model = LudwigModel.load(
self.transaction.lmd['ludwig_data']['ludwig_save_path'])
predictions = model.predict(data_df=predict_dataframe)
for col_name in predictions:
col_name_normalized = col_name.replace('_predictions', '')
predictions = predictions.rename(
columns={col_name: col_name_normalized})
return predictions
def initialize(config):
pth_mdl = os.path.join( config['pth_mdls'], config['model_to_load'], "model")
if not os.path.isdir(pth_mdl):
raise Exception("Could not find the model specified in the models directory: {}".format(pth_mdl))
global MODL, MMTA, FEAS_IN, FEAS_OUT
# load a model
st = time.time()
print("...loading model from {}".format(pth_mdl))
MODL = LudwigModel.load(pth_mdl)
with open(os.path.join(pth_mdl,"train_set_metadata.json")) as f: MMTA = json.load(f)
print("...loaded model in {:.2f}s".format(time.time()-st))
FEAS_IN = [fea for fea in MODL.model.hyperparameters['input_features']]
FEAS_OUT = [fea for fea in MODL.model.hyperparameters['output_features']]
input_features_desc, output_features_desc = "",""
for fea in FEAS_IN:
if fea['type'] == "image":
input_features_desc += "\t{}\t({}: {})\n".format(fea['name'],fea['type'],"({}, {}) {}".format(fea['width'],fea['height'],chan_count_to_mode(fea['num_channels'])))
else: input_features_desc += "\t{}\t({})\n".format(fea['name'],fea['type'])
for fea in FEAS_OUT:
if fea['type'] == "category":
fea['meta'] = MMTA[fea['name']]
output_features_desc += "\t{}\t(category with {} classes)\n".format(fea['name'],fea['num_classes'])
output_features_desc += "\t\t\t{}\n".format(", ".join(fea['meta']['idx2str']))
else:
output_features_desc += "\t{}\t({})\n".format(fea['name'],fea['type'])
#print(output_features)
console_msg = """#################### FRESH EYES ####################
I've just loaded a saved model from {0}
To check that the server is working, go to http://localhost:{1}/
It looks like the model I loaded requires the following inputs to make a prediction:
{2}
Make note of these names, as these particular fields will be required by API calls.
It looks like the following values will result from a prediction.
{3}
Make note of these as well, as these fields will be returned to API calls.
Invoke Cntl+C to stop the server
#################### FRESH EYES ####################
"""
print(console_msg.format(pth_mdl,config['port_num'],input_features_desc, output_features_desc))
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()
from flask import Flask, request, jsonify # loading in Flask
from ludwig import LudwigModel # loading in Ludwig
import pandas as pd # loading pandas for reading csv
# creating a Flask application
app = Flask(__name__)
# Load the model
model = LudwigModel.load('model')
# creating predict url and only allowing post requests.
@app.route('/predict', methods=['POST'])
def predict():
# Get data from Post request
data = request.get_json()
# Make prediction
df = pd.DataFrame([str(data['text'])], columns=['content'])
print(df.head())
# making predictions
pred = model.predict(data_df=df)
print(pred)
# returning the predictions as json
return jsonify(pred['airline_sentiment_predictions'][0])
if __name__ == '__main__':
app.run(port=3000, debug=True)
from tensorflow.contrib.training.python.training import hparam
from ludwig import LudwigModel
model_definition = {
"input_features": [{
"name": "doc_text",
"type": "text"
}],
"output_features": [{
"name": "class",
"type": "category"
}]
}
ludwig_model = LudwigModel(model_definition)
train_stats = ludwig_model.train(
data_csv="gs://skyl-dev-ml/playground/ludwig/train.csv")
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument(
'--train-files',
nargs='+',
help='Training file local or GCS',
default=
'gs://skyl-dev-ml/aashishdahiya/flowers_aashishdahiya_testV3_20181205_134432/preproc/train*'
)
parser.add_argument(
"type": "sequence",
"encoder": "rnn",
"cell_type": "lstm",
"bidirectional": true,
"num_layers": 2,
"reduce_output": null
}
],
"output_features": [
{
"name": "intent",
"type": "category",
"reduce_input": "sum",
"num_fc_layers": 1,
"fc_size": 64
}
]
}"""
model_definition = json.loads(data)
ludwig_model = LudwigModel(model_definition)
loaded_ludwig_model = ludwig_model
train_stats = ludwig_model.train(data_csv='train.csv')
ludwig_model.save(MODEL_PATH)
loaded_ludwig_model.load(MODEL_PATH)
predictions = loaded_ludwig_model.predict(data_csv='test.csv')
print(predictions)
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()
from flask import Flask, request, jsonify
from ludwig import LudwigModel
import pandas as pd
app = Flask(__name__)
#load the model
model = LudwigModel.load('./model')
@app.rout('/predict', method=['POST'])
def predict():
#get POST request data
data = request.get_json()
#Make prediction
df = pd.DataFrame([str(data['text'])], columns=['content'])
print(df.head())
pred = model.predict(data_df=df)
print(pred)
return jsonify(pred['airline_sentiment_predictions'][0])
if __name__ == '__main__':
app.run(port=4000, debug=True)
test_features = transform(test_df)
add_missing_dummy_columns(test_features, model_columns)
test_features = test_features[model_columns]
test_prediction = pd.DataFrame(model.predict(test_features),
columns=['prediction'])
submission = Ids.merge(test_prediction,
how='left',
left_index=True,
right_index=True)
submission.to_csv('submission.csv')
# Try with ludwig
# train a model
#load a model
model = LudwigModel.load(
"/Users/geoffrey.kip/Projects/ludwig/ludwig_models/results/experiment_run_1/model"
)
# obtain predictions
ludwig_predictions = model.predict(test_df)
#evaluate predictions
preds = np.where(predictions_probs[:, 1] >= 0.5, 1, 0)
print(accuracy_score(Y_test, preds))
print(confusion_matrix(Y_test, preds))
print(classification_report(Y_test, preds))
model.close()
'name': 'oldpeak',
'type': 'numerical',
'encoder': 'rnn'
}, {
'name': 'slope',
'type': 'category',
'encoder': 'rnn'
}, {
'name': 'ca',
'type': 'category',
'encoder': 'rnn'
}, {
'name': 'thal',
'type': 'category',
'encoder': 'rnn'
}],
'output_features': [{
'name': 'target',
'type': 'binary'
}],
'training': {
'epochs': 10
}
}
model = LudwigModel(model_definition)
train_stats = model.train(data)
# obtain predictions
predictions = model.predict(data)
model.close()
# import json
from ludwig import LudwigModel
import pandas as pd
# load the csv file
csv_file = pd.read_csv('out.csv')
model = LudwigModel.load(
"/home/jesse/Documents/Machine Learning/Disease Prediction System/Hepatitis/results/_run_4/model"
)
predict = model.predict(csv_file)
# convert prediit to json file
predict.to_json(r'./prediit.json')
},
{
'name': 'pe',
'type': 'category'
},
{
'name': 'ane',
'type': 'category'
},
],
'output_features': [{
'name': 'classification',
'type': 'binary'
}]
}
print('creating model')
model = LudwigModel(model_definition)
print('training model')
train_stats = model.train(data_df=train_df)
#Run predictions
predictions = model.predict(data_df=X_test)
predictions["classification_predictions"] = np.where(
predictions.iloc[:, 0] == True, 1, 0)
print(accuracy_score(Y_test, predictions.iloc[:, 0]))
print(confusion_matrix(Y_test, predictions.iloc[:, 0]))
print(classification_report(Y_test, predictions.iloc[:, 0]))
model.close()
