def run(args):
"""run the rating algorithms given the arguments.
Args:
args: the arguments.
"""
train = data.read_train(args.training_file, impute = False)
test = data.read_test(args.test_file)
start_time = time.time()
"""initialize the model."""
if args.rating_method == 'user-user':
model = rating.user_user(train, args.weighting_method, args.metric, args.k)
elif args.rating_method == 'movie-movie':
model = rating.item_item(train, args.weighting_method, args.metric, args.k)
elif args.rating_method == 'pcc':
model = rating.user_user(train, args.weighting_method, args.metric, args.k, True)
elif args.rating_method == 'bipartite-user':
clu_user = data.read_cluster(args.ucluster_file)
model = rating.bipartite_user(train, clu_user, args.weighting_method, args.metric, args.k)
elif args.rating_method == 'bipartite-movie':
clu_movie = data.read_cluster(args.mcluster_file)
model = rating.bipartite_item(train, clu_movie, args.weighting_method, args.metric, args.k)
"""predict the ratings. assume all models have a query API."""
py = []
for i, query in enumerate(test):
if i % 1000 == 0:
logging.info('{} out of {}'.format(i, len(test)))
py.append(model.query(query[0], query[1]))
"""time the program."""
end_time = time.time()
print 'running time =', end_time - start_time
"""output the prediction to files. used for test."""
if args.output_file:
fout = open(args.output_file, 'w')
for ppy in py:
fout.write('{}\n'.format(ppy))
fout.close()
"""evaluate the results. used for validation."""
if args.ground_truth:
gold = data.read_gold(args.ground_truth)
print 'RMSE =', math.sqrt(((gold - np.array(py)) ** 2).mean())
if __name__ == '__main__':
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
random.seed(0)
parser = argparse.ArgumentParser()
parser.add_argument('training_file', help = 'the file name of the training data')
parser.add_argument('output_movie', help = 'the output file for movie clusters')
parser.add_argument('output_user', help = 'the output file for user clusters')
parser.add_argument('--k_movie', help = 'the number of movie clusters', type = int, default = 200)
parser.add_argument('--k_user', help = 'the number of user clusters', type = int, default = 400)
parser.add_argument('--iter', help = 'the number of iterations', type = int, default = 10)
args = parser.parse_args()
mat = data.read_train(args.training_file, impute = True)
start_time = time.time()
res_row, res_col = bipartite(args.k_movie, args.k_user, args.iter, mat)
end_time = time.time()
fout = open(args.output_movie, 'w')
for e in res_row:
fout.write('{}\n'.format(e))
fout.close()
fout = open(args.output_user, 'w')
for e in res_col:
fout.write('{}\n'.format(e))
# -*- coding: utf-8 -*-
"""
Created on Sun Jun 10 15:37:16 2018
@author: ashima.garg
"""
import config
import data
import model
if __name__ == "__main__":
data = data.Data()
data.read_train(config.TRAIN_X_PATH, config.TRAIN_Y_PATH)
data.preprocess()
data.split()
print("data read")
model = model.Model()
model.build()
print("model build")
model.train(data)
print("model trained")
model.test(data)
print("model tested")
'''
data.read_test(config.TEST_X_PATH)
data.preprocess()
print("model predicted")
from nltk.corpus import stopwords
from sklearn.metrics import accuracy_score, confusion_matrix
from tensorflow.keras.preprocessing import sequence
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Embedding
from tensorflow.keras.layers import LSTM
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
#Train dataset
train_df = read_train(
"/Users/Ricou/Desktop/ANDRE/machine_learning/tweet_sentiment_extraction/data/train.csv"
)
print(train_df.head())
print(train_df.shape)
#Test dataset
test_df = read_test(
"/Users/Ricou/Desktop/ANDRE/machine_learning/tweet_sentiment_extraction/data/test.csv"
)
#print(test_df.head())
print(test_df.shape)
print("Text preprocessing")
#Recherche de valeurs manquantes sur le dataset train
print(f'Training null Values:\n{train_df.isnull().sum()}\n')
print(f'Test null Values:\n{test_df.isnull().sum()}')
def train_ld(): ds = data.Dataset() ds.datas = data.read_train() ld = data.Loader(ds, 1) return ld
