def main(in_file, out_file, x, y, epochs, ref=None, test=False, verbose=0):
if test:
df = pd.DataFrame(in_file, columns=range(in_file.shape[1]))
else:
df = pd.read_table(in_file, sep='\t', low_memory=True, index_col=0)
s = df.shape[0]
df.dropna(axis=0, how='any', inplace=True)
sn = df.shape[0]
if s != sn:
logger.warning('%d rows dropped due to missing values' % (s - sn))
s = df.shape[1]
df = df.select_dtypes(include=[np.number])
sn = df.shape[1]
if s != sn:
logger.warning('%d columns dropped due to non-numeric data type' % (s - sn))
basedir = os.path.dirname(os.path.abspath(__file__))
som = SOM(x, y)
if ref == 'IRCI':
som = som.load('/SOM.pkl')
embedding = som.winner_neurons(df.values)
else:
som.fit(df.values, epochs, verbose=verbose)
embedding = som.winner_neurons(df.values)
if ref == 'Create':
som.save(basedir + '/SOM.pkl')
emb_df = pd.DataFrame({'ID': df.index})
emb_df['X'] = embedding[:, 1]
emb_df['Y'] = embedding[:, 0]
if test:
return emb_df
else:
emb_df.to_csv(out_file, index=False, sep='\t')
#som.plot('result.png', 0)
#plt.figure(figsize=(8,8))
#i = 1
#for index in np.ndindex(som.shape):
# print(index, i)
# node_full = np.empty(tuple(variables[0].shape[1:])).flatten()
# mask = np.ma.getmaskarray(variables[0][0,:].flatten())
# print(node_full.shape, mask.shape)
#node_full[~mask] = som.nodes[index][:mask.shape[0]]*som.std[:mask.shape[0]] + som.mean[:mask.shape[0]]
# node_full[~mask] = som.nodes[index][:mask.shape[0]]
# node_full = node_full.reshape(tuple(variables[0].shape[1:]))
# node_full = np.ma.masked_greater(node_full, 1e9)
# print node_full.shape
# plt.subplot(som.shape[1], som.shape[0], i)
# plt.pcolormesh(np.squeeze(node_full))
# i += 1
#plt.savefig('result.png')
som.save('som.nc')
