So my task is to read data out of a .csv file and form clusters. My code works fine on a small .csv file but when i try to read the original file that i have to work on (it contains about 24k lines) my computer hangs and disk use shoots to 100% and i have t0 restart the system. I am at a dead end here and have no idea what's happening. the DBSCAN code is the same as provided as a demo on sklearn site. however the the code for reading the data i wrote myself
import csv
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import DBSCAN
from sklearn import metrics
#from sklearn.datasets.samples_generator import make_blobs
from sklearn.preprocessing import StandardScaler
import csv
def dbFun( _x,_original_vals):
db = DBSCAN(eps=0.3, min_samples=20).fit(_x)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_
#print(labels)
n_clusters_ = len(set(labels)) - (1 if -1 else 0)
print('Estimated number of clusters: %d' % n_clusters_)
print("Wait plotting clusters.....")
plotCluster(_x, labels, core_samples_mask, n_clusters_)
return
def plotCluster( _x, labels, core_samples_mask, n_clusters_):
unique_labels = set(labels)
colors = [plt.cm.Spectral(each)
for each in np.linspace(0, 1, len(unique_labels))]
for k, col in zip(unique_labels, colors):
if k == -1:
# Black used for noise.
col = [0, 0, 0, 1]
class_member_mask = (labels == k)
xy = _x[class_member_mask & core_samples_mask]
plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
markeredgecolor='k', markersize=14)
xy = _x[class_member_mask & ~core_samples_mask]
plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
markeredgecolor='k', markersize=6)
plt.title('Estimated number of clusters: %d' % n_clusters_)
plt.show()
return
_val = []
with open('C:/Users/hp 5th/Desktop/new1.csv', 'rU') as inp:
rd = csv.reader(inp)
for row in rd:
_val.append([row[1],row[2], row[0]])
#print(_center)
_val = np.asarray(_val)
_val_original = _val
_val_original =_val_original.astype('float32')
_val = StandardScaler().fit_transform(_val_original)
dbFun(_val, _val_original)
#_len = len(_center)