def run_clustering(X, k, dists_all):
cent, assign, shift, dists_cent = ksc.inc_ksc(X, k)
intra = metrics.avg_intra_dist(X, assign, dists_all)[0]
inter = metrics.avg_inter_dist(X, assign, dists_all)[0]
bcv = metrics.beta_cv(X, assign, dists_all)
cost = metrics.cost(X, assign, None, dists_cent)
return intra, inter, bcv, cost
def run_clustering(X, k, dists_all):
cent, assign, shift, dists_cent = ksc.inc_ksc(X, k)
intra = metrics.avg_intra_dist(X, assign, dists_all)[0]
inter = metrics.avg_inter_dist(X, assign, dists_all)[0]
bcv = metrics.beta_cv(X, assign, dists_all)
cost = metrics.cost(X, assign, None, dists_cent)
return intra, inter, bcv, cost
def main(tseries_fpath, base_folder, k):
k = int(k)
idx_fpath = os.path.join(os.path.join(base_folder, ".."), "train.dat")
X = ioutil.load_series(tseries_fpath, idx_fpath)
cent, assign, shift, dists_cent = ksc.inc_ksc(X, k)
np.savetxt(os.path.join(base_folder, "cents.dat"), cent, fmt="%.5f")
np.savetxt(os.path.join(base_folder, "assign.dat"), assign, fmt="%d")
np.savetxt(os.path.join(base_folder, "shift.dat"), shift, fmt="%d")
np.savetxt(os.path.join(base_folder, "dists_cent.dat"), dists_cent, fmt="%.5f")
def main(tseries_fpath, base_folder, k):
k = int(k)
idx_fpath = os.path.join(os.path.join(base_folder, '..'), 'train.dat')
X = ioutil.load_series(tseries_fpath, idx_fpath)
cent, assign, shift, dists_cent = ksc.inc_ksc(X, k)
np.savetxt(os.path.join(base_folder, 'cents.dat'), cent, fmt='%.5f')
np.savetxt(os.path.join(base_folder, 'assign.dat'), assign, fmt='%d')
np.savetxt(os.path.join(base_folder, 'shift.dat'), shift, fmt='%d')
np.savetxt(os.path.join(base_folder, 'dists_cent.dat'), dists_cent,
fmt='%.5f')
def main(tseries_fpath, k, plot_foldpath):
import mkl
mkl.set_num_threads(16)
initialize_matplotlib()
X = np.genfromtxt(tseries_fpath)[:, 1:]
aux = X.sum(axis=1)
fix = np.where(aux == 0)[0]
X[fix] += .001 #fixing zero only rows
X = X.copy()
cent, assign, shift, dists_cent = ksc.inc_ksc(X, k)
for i in range(cent.shape[0]):
t_series = cent[i]
plt.plot(t_series, '-k')
plt.gca().get_xaxis().set_visible(False)
plt.gca().get_yaxis().set_visible(False)
#plt.ylabel('Views')
#plt.xlabel('Time')
plt.savefig(os.path.join(plot_foldpath, '%d.pdf' % i))
plt.close()
half = t_series.shape[0] // 2
to_shift = half - np.argmax(t_series)
to_plot_peak_center = dist.shift(t_series, to_shift, rolling=True)
plt.plot(to_plot_peak_center, '-k')
plt.gca().get_xaxis().set_visible(False)
plt.gca().get_yaxis().set_visible(False)
#plt.ylabel('Views')
#plt.xlabel('Time')
plt.savefig(os.path.join(plot_foldpath, '%d-peak-center.pdf' % i))
plt.close()
to_shift = 0 - np.argmin(t_series)
to_plot_min_first = dist.shift(t_series, to_shift, rolling=True)
plt.plot(to_plot_min_first, '-k')
plt.gca().get_xaxis().set_visible(False)
plt.gca().get_yaxis().set_visible(False)
#plt.ylabel('Views')
#plt.xlabel('Time')
plt.savefig(os.path.join(plot_foldpath, '%d-min-first.pdf' % i))
plt.close()
np.savetxt(os.path.join(plot_foldpath, 'cents.dat'), cent, fmt='%.5f')
np.savetxt(os.path.join(plot_foldpath, 'assign.dat'), assign, fmt='%d')
np.savetxt(os.path.join(plot_foldpath, 'shift.dat'), shift, fmt='%d')
np.savetxt(os.path.join(plot_foldpath, 'dists_cent.dat'),
dists_cent,
fmt='%.5f')
def cluster(T, num_clust=5):
'''
Runs the KSC algorithm on time series matrix T.
Parameters
----------
T : ndarray of shape (row, time series length)
The time series to cluster
num_clust : int
Number of clusters to create
'''
T = np.asarray(T + 1e-20, order='C').copy()
cents, assign, _, _ = ksc.inc_ksc(T, num_clust)
return cents, assign
return ksc_input
if __name__ == "__main__":
df = pd.read_csv(
"new_daily_frequencies/zika_jj_cols_daily_frequencies_new.csv",
encoding="iso-8859-1")
# df = pd.read_csv("Frequencies.csv")
ksc_input = alter_inputs(df)
ksc_input = ksc_input.copy(order='C')
# ksc_input_values = ksc_input.values
#min_max_scaler = preprocessing.MinMaxScaler()
#x_scaled = min_max_scaler.fit_transform(ksc_input)
# ksc_input_normalized = pd.DataFrame(x_scaled)
k = 3 # Number of clusters
centers, assign, series_shifts, dists = ksc.inc_ksc(ksc_input, k)
# Creating a Dataframe to store Hashtags and Cluster
result_df = pd.DataFrame(columns=['Words', 'Cluster'])
result_df['Words'] = df['Words']
result_df['Cluster'] = assign
result_df.to_csv(
"new_daily_frequencies/Words_Daily_Frequencies_3Clusters.csv",
index=False,
encoding='utf-8')
