import logging
import csv
from sklearn import linear_model
from sklearn.grid_search import GridSearchCV
if __name__ == "__main__":
logging.basicConfig(format='--%(asctime)s:[%(levelname)s]:%(lineno)d:%(message)s', datefmt='%Y/%m/%d %H:%M:%S', level=logging.INFO)
logging.info("train_sgdc_cv.py Start")
p = PreProcess()
out_filepath = 'data/train_1M.csv.out'
#out_filepath = 'data/train_s404_100K.out.1vs1'
#out_filepath = 'data/train_1000.csv.out'
#Load data
X, y = p.load_train_data(out_filepath)
logging.info("Shape X = %r, y =%r" %(X.shape, y.shape ))
logging.info("example X = %s\ny =%r" %(X[0], y[0]))
logging.info("classes: %r" % list(np.unique(y)))
#Sampling
#At least 3
POWER = 6
CONST = 1
#At least 2
#CV = 5
n_subsamples = CONST*10**POWER
n_size = y.shape[0]
if n_subsamples < n_size:
logging.info("second index : %d to %d" % (n_size - n_subsamples/2, n_size))
X_small_train = X[range(n_subsamples/2)+range(n_size - n_subsamples/2, n_size)]
if __name__ == "__main__":
logging.basicConfig(
format="--%(asctime)s:[%(levelname)s]:%(lineno)d:%(message)s", datefmt="%Y/%m/%d %H:%M:%S", level=logging.INFO
)
logging.info("train_test.py Start")
SAMPLE = 50000
p = PreProcess()
train_filepath = "data/train_1M.csv.out"
# train_filepath = 'data/train_1000.csv.out'
# test_filepath = 'data/test.csv.out'
test_filepattern = "data/test_%d_M.out"
# Load train data
logging.info("Loading train set...")
X_train, y_train = p.load_train_data(train_filepath)
# Sampling
if y_train.shape[0] > SAMPLE:
X_train = X_train[:SAMPLE]
y_train = y_train[:SAMPLE]
else:
SAMPLE = y_train.shape[0]
logging.info("Sampling %d" % SAMPLE)
logging.info("Shape X_train = %r, y_train =%r" % (X_train.shape, y_train.shape))
logging.info("example X_train = %s\ny_train =%r" % (X_train[0], y_train[0]))
logging.info("classes: %r" % list(np.unique(y_train)))
# Training
# Default
C = 1.0
from sklearn.neighbors import KNeighborsClassifier
from sklearn.grid_search import GridSearchCV
if __name__ == "__main__":
logging.basicConfig(format='--%(asctime)s:[%(levelname)s]:%(lineno)d:%(message)s', datefmt='%Y/%m/%d %H:%M:%S', level=logging.INFO)
logging.info("train_knn_cv.py Start")
p = PreProcess()
#out_filepath = 'data/train_1M.csv.out'
#out_filepath = 'data/train_s404_10K.out'
out_filepath = 'data/train_1000.csv.out'
#Load data
#X, y = p.load_train_data(out_filepath)
#Load data with category
X, y, enc, map_dict = p.load_train_data(out_filepath, category = True)
logging.info("Shape X = %r, y =%r" %(X.shape, y.shape ))
logging.info("example X = %s\ny =%r" %(X[0], y[0]))
logging.info("classes: %r" % list(np.unique(y)))
#Sampling
#At least 3
POWER = 6
CONST = 1
#At least 2
n_subsamples = CONST*10**POWER
n_size = y.shape[0]
if n_subsamples < n_size:
logging.info("second index : %d to %d" % (n_size - n_subsamples/2, n_size))
X_small_train = X[range(n_subsamples/2)+range(n_size - n_subsamples/2, n_size)]
y_small_train = y[range(n_subsamples/2)+range(n_size - n_subsamples/2, n_size)]
