currentdir = os.path.dirname(
os.path.abspath(inspect.getfile(inspect.currentframe())))
parentdir = os.path.dirname(currentdir)
sys.path.insert(0, parentdir)
from datareader import DataReader
import word2vec as wv
import util
file_path = os.path.join(parentdir, "data")
file_path = os.path.join(file_path, "Wiki.txt")
eval_path = os.path.join(parentdir, "evaluation")
eval_path = os.path.join(eval_path, "questions-words-ptbr.txt")
my_data = DataReader(file_path)
my_data.get_data()
word2index = my_data.word2index
index2word = my_data.index2word
BATCH_SIZE = np.array(range(1, 17)) * 10
number_of_exp = len(BATCH_SIZE)
results = []
info = []
for i, bs in enumerate(BATCH_SIZE):
print("\n ({0} of {1})".format(i + 1, number_of_exp))
config = wv.Config(batch_size=bs)
attrs = vars(config)
config_info = ["%s: %s" % item for item in attrs.items()]
info.append(config_info)
my_model = wv.SkipGramModel(config)
plt.title("Actul vs Predicted Load ({}) - {} Window size {}".format(
location, "SVR_" + self.kernel_type, window_size))
plt.plot(list(range(len(preds))), testY, label='Actual Load')
plt.plot(list(range(len(preds))), preds, label='Predicted Load')
plt.xlabel('Time')
plt.ylabel('Power Consumption (MW)')
plt.legend()
plt.show()
return error
if __name__ == '__main__':
fname = "data/household.csv" # Works for household. Boosting does not.
location = os.path.split(fname)[1].split(".")[0]
datareader = DataReader(fname, sample_size=10000, encoding='Cosine')
features, Y = datareader.get_data()
window_size = 7
# 7 does not predict higher extreme values
# 28 does not predict lower extreme values
features = features[:-window_size]
X, Y = window(Y, window_size)
X = np.concatenate((X, features), axis=1)
svm_poly = SVRRegression(kernel_type='poly')
loss = svm_poly.fit_predict(X, Y, location)
print("Loss : ", "%.2f" % loss)
class RegressionDataset(Dataset):
def __init__(self, inputs, labels):
self.inputs = inputs
self.labels = labels
def __len__(self):
return len(self.inputs)
def __getitem__(self, id):
sample = self.inputs[id], self.labels[id]
return sample
if __name__ == '__main__':
fname = "data/AEP_hourly.csv"
datareader = DataReader(fname)
X, Y = datareader.get_data()
dataset = RegressionDataset(inputs=X, labels=Y)
dataset_loader = DataLoader(dataset,
batch_size=8,
shuffle=False,
num_workers=2)
for i, [input, label] in enumerate(dataset_loader):
print(input)
print(label)
print()
if i == 2: break
def test_run():
'''function to test all the utlities'''
# Define a date range
dates = pd.date_range('2015-04-02', '2016-04-01')
# Choose feature symbols to read
location = os.path.join(base_dir, "BitcoinData")
symbols = os.listdir(location)
#build dataframe consisting of all features
dfreader = DataReader()
util = Utility()
location = os.path.join(base_dir, "BitcoinData")
df = dfreader.get_data(location, symbols, dates)
df = util.normalize_data(df)
for index in range(len(symbols)):
symbols[index] = symbols[index].strip('.csv')
plotter = DataPlotting()
#plot dataframe in selected range and given features list
plotter.plot_selected(df, symbols, '2015-05-01', '2015-06-01')
#plot dataframe for all given data
plotter.plot_data(df, "Bitcoin")
dates = pd.date_range('2010-01-01', '2016-01-01')
btc_file = "bitcoin-market-price.csv"
location = os.path.join(base_dir, btc_file)
df_btc = dfreader.get_btc(location, btc_file, dates)
stats = Statistics(df)
rmean = stats.get_rolling_mean(df_btc['bitcoin-market-price'], window=20)
rstd = stats.get_rolling_std(df_btc.ix[:, 'bitcoin-market-price'], window=20)
upper_band, lower_band = stats.get_bollinger_bands(rmean, rstd)
# Plot raw values, rolling mean and Bollinger Bands
ax = df_btc['bitcoin-market-price'].plot(title="Bollinger Bands", \
label='bitcoin-market-price')
rmean.plot(label='Rolling mean', ax=ax)
upper_band.plot(label='upper band', ax=ax)
lower_band.plot(label='lower band', ax=ax)
# Add axis labels and legend
ax.set_xlabel("Date")
ax.set_ylabel("Price")
ax.legend(loc='upper left')
plt.show()
#compute daily returns
daily_returns = stats.compute_daily_returns(df_btc)
plotter.plot_data(daily_returns, title="Daily returns", ylabel="Daily returns")
daily_returns.replace(to_replace=np.inf, value=np.NaN, inplace=True)
# Plot a histogram
daily_returns.hist(bins=21)
# Get mean as standard deviation
mean = daily_returns.mean()
std = daily_returns.std()
#print type(mean)
plt.axvline(mean[0], color='w', linestyle='dashed', linewidth=2)
plt.axvline(std[0], color='r', linestyle='dashed', linewidth=2)
plt.axvline(-std[0], color='r', linestyle='dashed', linewidth=2)
plt.show()
# Scatterplots
df.plot(kind='scatter', x='hash_rate', y='market_cap')
beta_XOM, alpha_XOM = np.polyfit(df['hash_rate'], df['market_cap'], 1) # fit poly degree 1
plt.plot(df['hash_rate'], beta_XOM*df['market_cap'] + alpha_XOM, '-', color='r')
plt.show()
# Calculate correlation coefficient
correlation = df['avg_block_size'].corr(df['n_tx'], method='pearson')
print correlation