def main():
train_data, test_data = read_file(train_file_name), read_file(
test_file_name)
cleaned_train_data, cleaned_test_data = preform_pre_processing(
train_data), preform_pre_processing(test_data)
print('========== Question 1 ==========')
run_q1(cleaned_train_data, cleaned_test_data)
print('========== Question 2 ==========')
run_q2(cleaned_train_data, cleaned_test_data)
#!/usr/bin/env python
import matplotlib.pyplot as plt
from waveform import Waveform
import data_reader
import sys
if __name__ == '__main__':
w = data_reader.read_file(sys.argv[-1])
peaks = w.ft_peaks()
fx, fy = w.abs_dft()
plt.plot(fx, fy)
for peak in peaks:
plt.plot(fx[peak], fy[peak], marker='o', color='r')
plt.show()
import spacy
from spacy.util import minibatch, compounding
import sys
import data_reader
import argparse
import ast
parser = argparse.ArgumentParser(description='Proccess excel file and train data')
parser.add_argument('-f')
parser.add_argument('-sh')
parser.add_argument('-m')
parser.add_argument('-o')
args = vars(parser.parse_args())
# training data
TRAIN_DATA = data_reader.read_file(args['f'], args['sh'])
@plac.annotations(
model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
file=("File of excel.", "option", "f", str),
sheet=("Sheetname of excel.", "option", "sh", str),
output_dir=("Optional output directory", "option", "o", Path),
n_iter=("Number of training iterations", "option", "n", int))
def main(model=None, output_dir=None, n_iter=100, file=None, sheet=None):
"""Load the model, set up the pipeline and train the entity recognizer."""
if model is not None:
nlp = spacy.load(model) # load existing spaCy model
print("Loaded model '%s'" % model)
else:
nlp = spacy.blank('en') # create blank Language class
bbpg = player.random_poisson('BB')
points = player.score(opg, hpg, hbpg, bbpg, wpg, erpg, lpg, spg,
kpg)
else:
tb = player.random_poisson('TB')
r = player.random_poisson('R')
bb = player.random_poisson('BB')
rbi = player.random_poisson('RBI')
cs = player.random_poisson('CS')
sb = player.random_poisson('SB')
k = player.random_poisson('K')
points = player.score(tb, r, bb, rbi, cs, sb, k)
return (points)
players = data_reader.read_file('./2017Players.csv')
for p in players:
p.points_per_game()
pitchers = data_reader.read_file('./2017Pitchers.csv', True)
for p in pitchers:
p.points_per_game()
players = [x for x in players if not x.pitcher]
pitchers.sort(key=lambda x: x.ppg, reverse=True)
players.sort(key=lambda x: x.ppg, reverse=True)
my_team = Team()
other_team = Team()
teams = [my_team, other_team]
no_plays = [x for x in players + pitchers if x.sim_plays < 50]
while len(no_plays) > 0:
topPosPlayers = players[:250]
from waveform import Waveform
import data_reader
if __name__ == '__main__':
waveforms = []
xs = []
ys = []
for trial in ['Trial_6']:
datafiles = sorted(os.listdir(os.path.join(sys.argv[-1], trial)),
key=lambda item:
(int(item.partition(' ')[0])
if item[0].isdigit() else float('inf'), item))
print(datafiles)
for datum in datafiles:
w = data_reader.read_file(os.path.join(sys.argv[-1], trial, datum))
waveforms.append(w)
for w in waveforms:
x, y = w.abs_dft()
peaks = w.ft_peaks()
xs.append(x[peaks[0]])
ys.append(y[peaks[0]])
#plt.plot(x, y)
#plt.plot(x[peaks[0]], y[peaks[0]], marker='o', color='r')
#plt.show()
sorted_x = sorted(xs)
sorted_y = [x for _, x in sorted(zip(ys, xs))]
plt.plot(sorted_x, sorted_y)
#!/usr/bin/env python
import matplotlib.pyplot as plt
import data_reader
import sys
if __name__ == '__main__':
data_reader.read_file(sys.argv[-1]).plot()
plt.show()