def get_train_cv_data_by_chunk(data):
chunk_map = utilities.get_chunk_map(data, 1)
train_data = []
cv_data = []
for chunk_id in chunk_map.keys():
num = len(chunk_map[chunk_id])
train_num = 147
train_data += chunk_map[chunk_id][0:train_num]
cv_data += chunk_map[chunk_id][train_num::]
return train_data, cv_data
def get_train_cv_data_by_chunk(data):
chunk_map = utilities.get_chunk_map(data, 1)
train_data = []
cv_data = []
for chunk_id in chunk_map.keys():
num = len(chunk_map[chunk_id])
train_num = 147
train_data += chunk_map[chunk_id][0 : train_num]
cv_data += chunk_map[chunk_id][train_num : :]
return train_data, cv_data
def time_series(training_file, submission_file, output_file):
data = utilities.read_file(training_file, True)
first_line = data[0]
data = data[1 : :]
data = preprocess.fill_NAs(data)
(chunk_avg, hour_avg_by_chunk, weekday_avg_by_chunk,
hour_avg, weekday_avg) = feature_extraction.get_avg_maps(data)
clf_map = regression.linear_regression_2(data)
print 'Filling submission file...'
chunk_map = utilities.get_chunk_map(data, 1)
sub_data = utilities.read_file(submission_file, True)
positions = [1, 2, 3, 4, 5, 10, 17, 24, 48, 72]
for i in range(1, len(sub_data)):
chunk_id = sub_data[i][1]
hour = sub_data[i][3]
pos = positions[(i - 1) % 10]
for j in range(5, len(sub_data[i])):
target = j - 5
if sub_data[i][j] == '0':
if not chunk_id in chunk_map:
sub_data[i][j] = hour_avg[hour][target]
else:
data_in_chunk = chunk_map[chunk_id]
start = len(data_in_chunk) - 24
t = len(data_in_chunk[0]) - 39 + target
features = []
prev_hour = 0
for k in range(start, len(data_in_chunk)):
features.append(float(data_in_chunk[k][t]))
if data_in_chunk[k][5] == hour:
prev_hour = float(data_in_chunk[k][t])
features.append(prev_hour)
# Binary hour features.
for h in range(24):
if h == int(hour):
features.append(1)
else:
features.append(0)
# Binary month features.
month = int(sub_data[i][4])
for m in range(1, 13):
if m == month:
features.append(1)
else:
features.append(0)
# Weather features.
tmp_length = len(data_in_chunk)
for k in range(6, 56):
features.append(float(data_in_chunk[tmp_length - 1][k]))
for k in range(6, 56):
features.append(float(data_in_chunk[tmp_length - 2][k]))
sub_data[i][j] = \
clf_map[(target, pos)].predict([features])[0]
utilities.write_file(output_file, sub_data)
def time_series(training_file, submission_file, output_file):
data = utilities.read_file(training_file, True)
first_line = data[0]
data = data[1::]
data = preprocess.fill_NAs(data)
(chunk_avg, hour_avg_by_chunk, weekday_avg_by_chunk, hour_avg,
weekday_avg) = feature_extraction.get_avg_maps(data)
clf_map = regression.linear_regression_2(data)
print 'Filling submission file...'
chunk_map = utilities.get_chunk_map(data, 1)
sub_data = utilities.read_file(submission_file, True)
positions = [1, 2, 3, 4, 5, 10, 17, 24, 48, 72]
for i in range(1, len(sub_data)):
chunk_id = sub_data[i][1]
hour = sub_data[i][3]
pos = positions[(i - 1) % 10]
for j in range(5, len(sub_data[i])):
target = j - 5
if sub_data[i][j] == '0':
if not chunk_id in chunk_map:
sub_data[i][j] = hour_avg[hour][target]
else:
data_in_chunk = chunk_map[chunk_id]
start = len(data_in_chunk) - 24
t = len(data_in_chunk[0]) - 39 + target
features = []
prev_hour = 0
for k in range(start, len(data_in_chunk)):
features.append(float(data_in_chunk[k][t]))
if data_in_chunk[k][5] == hour:
prev_hour = float(data_in_chunk[k][t])
features.append(prev_hour)
# Binary hour features.
for h in range(24):
if h == int(hour):
features.append(1)
else:
features.append(0)
# Binary month features.
month = int(sub_data[i][4])
for m in range(1, 13):
if m == month:
features.append(1)
else:
features.append(0)
# Weather features.
tmp_length = len(data_in_chunk)
for k in range(6, 56):
features.append(float(data_in_chunk[tmp_length -
1][k]))
for k in range(6, 56):
features.append(float(data_in_chunk[tmp_length -
2][k]))
sub_data[i][j] = \
clf_map[(target, pos)].predict([features])[0]
utilities.write_file(output_file, sub_data)