0

I am using this code for DBSCAN algorithm. However, instead of generating random sample data, I want to import my own .csv file. I am not so good at python so all my attempts failed.

print(__doc__)

import numpy as np

from sklearn.cluster import DBSCAN
from sklearn import metrics
from sklearn.datasets import make_blobs
from sklearn.preprocessing import StandardScaler


# #############################################################################
# Generate sample data
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=750, centers=centers, cluster_std=0.4,
                        random_state=0)

X = StandardScaler().fit_transform(X)

# #############################################################################
# Compute DBSCAN
db = DBSCAN(eps=0.3, min_samples=10).fit(X)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_

# Number of clusters in labels, ignoring noise if present.
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
n_noise_ = list(labels).count(-1)

print('Estimated number of clusters: %d' % n_clusters_)
print('Estimated number of noise points: %d' % n_noise_)
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
print("Adjusted Rand Index: %0.3f"
  % metrics.adjusted_rand_score(labels_true, labels))
print("Adjusted Mutual Information: %0.3f"
  % metrics.adjusted_mutual_info_score(labels_true, labels))
print("Silhouette Coefficient: %0.3f"
  % metrics.silhouette_score(X, labels))

# #############################################################################
# Plot result
import matplotlib.pyplot as plt

# Black removed and is used for noise instead.
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()

My question is: How would I edit the code to load my own .csv file and perform the algorithm on my own dataset?

anAbsoluteDevil
  • 3
  • 1
  • Please provide some of your attempts, this is a question/answer website, not a "request algorithm" one. Moreover in your case it should be really easy with `pandas`'s `read_csv` function, have you tried it? – RandomGuy May 19 '21 at 07:42
  • @RandomGuys yes, have tried pandas. I tried this `dataset = pd.read_csv('dataset.csv') X, labels_true = dataset.iloc[:, [1,2,3,4,5,6,7,8,9,10,11,12,13,14]].values` however i got this error:ValueError: too many values to unpack (expected 2) – anAbsoluteDevil May 19 '21 at 07:49
  • https://stackoverflow.com/questions/50243128/pandas-for-loop-over-dataframe-gives-too-many-values-to-unpack – David Thery May 19 '21 at 10:06

1 Answers1

0

You should use pandas, as follows:

import numpy as np
import pandas as pd

input_file = "yourdata.csv"

# comma delimited is the default
df = pd.read_csv(input_file, header = 0)

You can find a more extensive example on Kaggle.

David Thery
  • 669
  • 1
  • 6
  • 21