I have a dataframe like below. The shape is (24,7)
Name x1 x2 x3 x4 x5 x6
Harry 102 204 0.43 0.21 1.02 0.39
James 242 500 0.31 0.11 0.03 0.73
.
.
.
Mike 3555 4002 0.12 0.03 0.52. 0.11
Henry 532 643 0.01 0.02 0.33 0.10
I want to run Scikit-learn's Different Clustering Algorithms Script on the above dataframe. However, the input data looks quite confusing, not too sure how to input my dataframe
CodePudding user response：
PS : please replace : data = X_data.iloc[:20000] by your X
import numpy as np
import matplotlib as plt
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn import decomposition
from sklearn import preprocessing
from sklearn import cluster, metrics
from scipy.cluster.hierarchy import linkage, fcluster
from sklearn import preprocessing
from collections import Counter
from sklearn.cluster import DBSCAN
from sklearn import mixture
from sklearn.preprocessing import StandardScaler
from sklearn import metrics
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_samples, silhouette_score
comp_model = pd.DataFrame(columns=['Model', 'Score_Silhouette',
'num_clusters', 'size_clusters',
'parameters'])
K-Means :
def k_means(X_data, nb_clusters, model_comp):
ks = nb_clusters
inertias = []
data = X_data.iloc[:20000]
X = data.values
X_scaled = preprocessing.StandardScaler().fit_transform(X)
for num_clusters in ks:
# Create a KMeans instance with k clusters: model
model = KMeans(n_clusters=num_clusters, n_init=1)
# Fit model to samples
model.fit(X_scaled)
# Append the inertia to the list of inertias
inertias.append(model.inertia_)
silh = metrics.silhouette_score(X_scaled, model.labels_)
# Counting the amount of data in each cluster
taille_clusters = Counter(model.labels_)
data = [{'Model': 'kMeans',
'Score_Silhouette': silh,
'num_clusters': num_clusters,
'size_clusters': taille_clusters,
'parameters': 'nb_clusters :' str(num_clusters)}]
model_comp = model_comp.append(data, ignore_index=True, sort=False)
# Plot ks vs inertias
plt.plot(ks, inertias, '-o')
plt.xlabel('number of clusters, k')
plt.ylabel('inertia')
plt.xticks(ks)
plt.show()
return model_comp
comp_model = k_means(X_data=df,
nb_clusters=pd.np.arange(2, 11, 1),
model_comp=comp_model)
DBscan :
def dbscan_grid_search(X_data, model_comp, eps_space=0.5,
min_samples_space=5, min_clust=0, max_clust=10):
data = X_data.iloc[:20000]
X = data.values
X_scaled = preprocessing.StandardScaler().fit_transform(X)
# Starting a tally of total iterations
n_iterations = 0
# Looping over each combination of hyperparameters
for eps_val in eps_space:
for samples_val in min_samples_space:
dbscan_grid = DBSCAN(eps=eps_val,
min_samples=samples_val)
# fit_transform
clusters = dbscan_grid.fit_predict(X=X_scaled)
# Counting the amount of data in each cluster
cluster_count = Counter(clusters)
#n_clusters = sum(abs(pd.np.unique(clusters))) - 1
n_clusters = len(set(clusters)) - (1 if -1 in clusters else 0)
# Increasing the iteration tally with each run of the loop
n_iterations = 1
# Appending the lst each time n_clusters criteria is reached
if n_clusters >= min_clust and n_clusters <= max_clust:
silh = metrics.silhouette_score(X_scaled, clusters)
data = [{'Model': 'Dbscan',
'Score_Silhouette': silh,
'num_clusters': n_clusters,
'size_clusters': cluster_count,
'parameters': 'eps :' str(eps_val) ' samples_val :' str(samples_val)}]
model_comp = model_comp.append(
data, ignore_index=True, sort=False)
return model_comp
comp_model = dbscan_grid_search(X_data=df,
model_comp=comp_model,
eps_space=pd.np.arange(0.1, 5, 0.6),
min_samples_space=pd.np.arange(1, 30, 3),
min_clust=2,
max_clust=10)
GMM :
def gmm(X_data, nb_clusters, model_comp):
ks = nb_clusters
data = X_data.iloc[:20000]
X = data.values
X_scaled = preprocessing.StandardScaler().fit_transform(X)
for num_clusters in ks:
# Create a KMeans instance with k clusters: model
gmm = mixture.GaussianMixture(n_components=num_clusters).fit(X_scaled)
# Fit model to samples
gmm.fit(X_scaled)
pred = gmm.predict(X_scaled)
cluster_count = Counter(pred)
silh = metrics.silhouette_score(X_scaled, pred)
data = [{'Model': 'GMM',
'Score_Silhouette': silh,
'num_clusters': num_clusters,
'size_clusters': cluster_count,
'parameters': 'nb_clusters :' str(num_clusters)}]
model_comp = model_comp.append(data, ignore_index=True, sort=False)
return model_comp
comp_model = gmm(X_data=df,
nb_clusters=pd.np.arange(2, 11, 1),
model_comp=comp_model
)
At the end you will have comp_model which will contain all the results of your algo. Here I am using three algorithms, after you selected the best fit for you (with score silhouette and number of cluster).
You should check the repartitions of each cluster : https://scikit-learn.org/stable/auto_examples/cluster/plot_kmeans_silhouette_analysis.html#sphx-glr-auto-examples-cluster-plot-kmeans-silhouette-analysis-py
CodePudding user response：
There are two main differences between your scenario and the scikit-learn example you link to:
- You only have one dataset, not several different ones to compare.
- You have six features, not just two.
Point one allows you to simplify the example code by deleting the loops over the different datasets and related calculations. Point two implies that you cannot easily plot your results. Instead, you could just add the predicted class labels found by each algorithm to your dataset.
So you could modify the example code like this:
import time
import warnings
import numpy as np
import pandas as pd
from sklearn import cluster, datasets, mixture
from sklearn.neighbors import kneighbors_graph
from sklearn.preprocessing import StandardScaler
from itertools import cycle, islice
np.random.seed(0)
# ============
# Introduce your dataset
# ============
my_df = # Insert your data here, as a pandas dataframe.
features = [f'x{i}' for i in range(1, 7)]
X = my_df[features].values
# ============
# Set up cluster parameters
# ============
params = {
"quantile": 0.3,
"eps": 0.3,
"damping": 0.9,
"preference": -200,
"n_neighbors": 3,
"n_clusters": 3,
"min_samples": 7,
"xi": 0.05,
"min_cluster_size": 0.1,
}
# normalize dataset for easier parameter selection
X = StandardScaler().fit_transform(X)
# estimate bandwidth for mean shift
bandwidth = max(cluster.estimate_bandwidth(X, quantile=params["quantile"]),
0.001) # arbitrary correction to avoid 0
# connectivity matrix for structured Ward
connectivity = kneighbors_graph(
X, n_neighbors=params["n_neighbors"], include_self=False
)
# make connectivity symmetric
connectivity = 0.5 * (connectivity connectivity.T)
# ============
# Create cluster objects
# ============
ms = cluster.MeanShift(bandwidth=bandwidth, bin_seeding=True)
two_means = cluster.MiniBatchKMeans(n_clusters=params["n_clusters"])
ward = cluster.AgglomerativeClustering(
n_clusters=params["n_clusters"], linkage="ward", connectivity=connectivity
)
spectral = cluster.SpectralClustering(
n_clusters=params["n_clusters"],
eigen_solver="arpack",
affinity="nearest_neighbors",
)
dbscan = cluster.DBSCAN(eps=params["eps"])
optics = cluster.OPTICS(
min_samples=params["min_samples"],
xi=params["xi"],
min_cluster_size=params["min_cluster_size"],
)
affinity_propagation = cluster.AffinityPropagation(
damping=params["damping"], preference=params["preference"], random_state=0
)
average_linkage = cluster.AgglomerativeClustering(
linkage="average",
affinity="cityblock",
n_clusters=params["n_clusters"],
connectivity=connectivity,
)
birch = cluster.Birch(n_clusters=params["n_clusters"])
gmm = mixture.GaussianMixture(
n_components=params["n_clusters"], covariance_type="full"
)
clustering_algorithms = (
("MiniBatch\nKMeans", two_means),
("Affinity\nPropagation", affinity_propagation),
("MeanShift", ms),
("Spectral\nClustering", spectral),
("Ward", ward),
("Agglomerative\nClustering", average_linkage),
("DBSCAN", dbscan),
("OPTICS", optics),
("BIRCH", birch),
("Gaussian\nMixture", gmm),
)
for name, algorithm in clustering_algorithms:
t0 = time.time()
# catch warnings related to kneighbors_graph
with warnings.catch_warnings():
warnings.filterwarnings(
"ignore",
message="the number of connected components of the "
"connectivity matrix is [0-9]{1,2}"
" > 1. Completing it to avoid stopping the tree early.",
category=UserWarning,
)
warnings.filterwarnings(
"ignore",
message="Graph is not fully connected, spectral embedding"
" may not work as expected.",
category=UserWarning,
)
algorithm.fit(X)
t1 = time.time()
if hasattr(algorithm, "labels_"):
y_pred = algorithm.labels_.astype(int)
else:
y_pred = algorithm.predict(X)
# Add cluster labels to the dataset
my_df[name] = y_pred