Unsupervised_Learning_Codes.py

# Import KMeans
from sklearn.cluster import KMeans

# Create a KMeans instance with 3 clusters: model
model = KMeans(n_clusters=3)

# Fit model to points
model.fit(points)

# Determine the cluster labels of new_points: labels
labels = model.predict(new_points)

# Print cluster labels of new_points
print(labels)

#---------- How to draw with the new points and create centroid out of it ---------

# Import pyplot
from matplotlib import pyplot as plt

# Assign the columns of new_points: xs and ys
xs = new_points[:,0]
ys = new_points[:,1]

# Make a scatter plot of xs and ys, using labels to define the colors
plt.scatter(xs, ys, c=labels, alpha=0.5)

# Assign the cluster centers: centroids
centroids = model.cluster_centers_

# Assign the columns of centroids: centroids_x, centroids_y
centroids_x = centroids[:,0]
centroids_y = centroids[:,1]

# Make a scatter plot of centroids_x and centroids_y
plt.scatter(centroids_x, centroids_y, marker='D', s=50)
plt.show()
---------------------------------------------------------------------------------------

##### Evaluate the clusters (elbow method) ###################

ks = range(1, 6)
inertias = []

for k in ks:
    # Create a KMeans instance with k clusters: model
    model = KMeans(n_clusters=k)
    
    
    # Fit model to samples
    model.fit(samples)
    
    # Append the inertia to the list of inertias
    inertias.append(model.inertia_)
    
# Plot ks vs inertias
plt.plot(ks, inertias, '-o')
plt.xlabel('number of clusters, k')
plt.ylabel('inertia')
plt.xticks(ks)
plt.show()
-------------

########## How to understand your cluster if already some label is there --- solution is CROSSTAB -----------------

# Create a KMeans model with 3 clusters: model
model = KMeans(n_clusters=3)

# Use fit_predict to fit model and obtain cluster labels: labels
labels = model.fit_predict(samples) ## it is same - fit followed by method 

# Create a DataFrame with labels and varieties as columns: df
df = pd.DataFrame({'labels': labels, 'varieties': varieties})

# Create crosstab: ct
ct = pd.crosstab(df['labels'],df['varieties']) ## varieties is already label 

# Display ct
print(ct)

------------------

NORMLIZER SCALING FUNCTION 
------------------

'''
Clustering stocks using KMeans
In this exercise, you'll cluster companies using their daily stock price movements (i.e. the dollar difference between the closing and opening prices for each trading day). You are given a NumPy array movements of daily price movements from 2010 to 2015 (obtained from Yahoo! Finance), where each row corresponds to a company, and each column corresponds to a trading day.

Some stocks are more expensive than others. To account for this, include a Normalizer at the beginning of your pipeline. The Normalizer will separately transform each company's stock price to a relative scale before the clustering begins.

Note that Normalizer() is different to StandardScaler(), which you used in the previous exercise. While StandardScaler() standardizes features (such as the features of the fish data from the previous exercise) by removing the mean and scaling to unit variance, Normalizer() rescales each sample - here, each company's stock price - independently of the other
'''

# Import Normalizer
from sklearn.preprocessing import Normalizer

# Create a normalizer: normalizer
normalizer = Normalizer()

# Create a KMeans model with 10 clusters: kmeans
kmeans = KMeans(n_clusters=10)

# Make a pipeline chaining normalizer and kmeans: pipeline
pipeline = make_pipeline(normalizer,kmeans)

# Fit pipeline to the daily price movements
pipeline.fit(movements)

# Import pandas
import pandas as pd

# Predict the cluster labels: labels
labels = pipeline.predict(movements)

# Create a DataFrame aligning labels and companies: df
df = pd.DataFrame({'labels': labels, 'companies': companies})

# Display df sorted by cluster label
print(df.sort_values('labels')) ##### this results give us that which company's share are moving closely 

-------------------------------------
HIERARCIAL CLUSTERING
--------------------------------------

# Perform the necessary imports
from scipy.cluster.hierarchy import linkage,dendrogram
import matplotlib.pyplot as plt

# Calculate the linkage: mergings
mergings = linkage(samples,method='complete')

# Plot the dendrogram, using varieties as labels
dendrogram(mergings,
           labels=varieties,
           leaf_rotation=90,
           leaf_font_size=6,
)
plt.show()
#-------------------------------------------------------
# Import normalize
from sklearn.preprocessing import normalize

# Normalize the movements: normalized_movements
normalized_movements = normalize(movements)

# Calculate the linkage: mergings
mergings = linkage(normalized_movements, method='complete')

# Plot the dendrogram
dendrogram(
    mergings,
    labels=companies,
    leaf_rotation=90.,
    leaf_font_size=6
)
plt.show()

-------------------------------------------------------
'''
We used a method called -- 'complete' that is max distance between the clusters 
In the video, you learned that the linkage method defines how the distance between clusters is measured. In complete linkage, the distance between clusters is the distance between the furthest points of the clusters. In single linkage, the distance between clusters is the distance between the closest points of the clusters.
'''
# Perform the necessary imports
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import linkage, dendrogram

# Calculate the linkage: mergings
mergings = linkage(samples, method='single')

# Plot the dendrogram
dendrogram(mergings,
           labels=country_names,
           leaf_rotation=90,
           leaf_font_size=6,
)
plt.show()
----------------------------------------------------------
------- FLUSTER  & CROSSTAB-----------------------

# Perform the necessary imports
import pandas as pd
from scipy.cluster.hierarchy import fcluster

# Use fcluster to extract labels: labels
labels = fcluster(mergings, 6, criterion='distance')

# Create a DataFrame with labels and varieties as columns: df
df = pd.DataFrame({'labels': labels, 'varieties': varieties})

# Create crosstab: ct
ct = pd.crosstab(df['labels'], df['varieties'])

# Display ct
print(ct)
------------------------

----------------TSNE -------
# Import TSNE
from sklearn.manifold import TSNE

# Create a TSNE instance: model
model = TSNE(learning_rate=200)

# Apply fit_transform to samples: tsne_features
tsne_features = model.fit_transform(samples)

# Select the 0th feature: xs
xs = tsne_features[:,0]

# Select the 1st feature: ys
ys = tsne_features[:,1]

# Scatter plot, coloring by variety_numbers
plt.scatter(xs, ys, c=variety_numbers)
plt.show()
---------------------------------------------
#------------ TSNE MAP for a stok Market case -------------

# Import TSNE
from sklearn.manifold import TSNE 

# Create a TSNE instance: model
model = TSNE(learning_rate=50)

# Apply fit_transform to normalized_movements: tsne_features
tsne_features = model.fit_transform(normalized_movements)

# Select the 0th feature: xs
xs = tsne_features[:,0]

# Select the 1th feature: ys
ys = tsne_features[:,1]

# Scatter plot
plt.scatter(xs,ys,alpha=0.5)

# Annotate the points
for x, y, company in zip(xs, ys, companies):
    plt.annotate(company, (x, y), fontsize=5, alpha=0.75)
plt.show()
----------------------------------------------------------
------------------------ PCA ----------------------------

# Import PCA
from sklearn.decomposition import PCA

# Create PCA instance: model
model = PCA()

# Apply the fit_transform method of model to grains: pca_features
pca_features = model.fit_transform(grains)

# Assign 0th column of pca_features: xs
xs = pca_features[:,0]

# Assign 1st column of pca_features: ys
ys = pca_features[:,1]

# Scatter plot xs vs ys
plt.scatter(xs, ys)
plt.axis('equal')
plt.show()

# Calculate the Pearson correlation of xs and ys
correlation, pvalue = pearsonr(xs, ys)

# Display the correlation
print(correlation)
-----------------------------------------------------------
-------- BI-Plot ----------------

# Make a scatter plot of the untransformed points
plt.scatter(grains[:,0], grains[:,1])

# Create a PCA instance: model
model = PCA()

# Fit model to points
model.fit(grains)

# Get the mean of the grain samples: mean
mean = model.mean_

# Get the first principal component: first_pc
first_pc = model.components_[0]

# Plot first_pc as an arrow, starting at mean
plt.arrow(mean[0], mean[1], first_pc[0], first_pc[1], color='red', width=0.01)

# Keep axes on same scale
plt.axis('equal')
plt.show()
----------------------------------
How many factor to choose using PCA 
----------------------------------

# Perform the necessary imports
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import make_pipeline
import matplotlib.pyplot as plt

# Create scaler: scaler
scaler = StandardScaler()

# Create a PCA instance: pca
pca = PCA()

# Create pipeline: pipeline
pipeline = make_pipeline(scaler,pca)

# Fit the pipeline to 'samples'
pipeline.fit(samples)

# Plot the explained variances
features = range(pca.n_components_)
plt.bar(features,pca.explained_variance_)
plt.xlabel('PCA feature')
plt.ylabel('variance')
plt.xticks(features)
plt.show()

-----------------------------------------------------------------
How to reduce dimenion for a data set into some reduced features 
-----------------------------------------------------------------
# Import PCA
from sklearn.decomposition import PCA 

# Create a PCA model with 2 components: pca
pca = PCA(n_components=2)

# Fit the PCA instance to the scaled samples
pca.fit(scaled_samples)

# Transform the scaled samples: pca_features
pca_features = pca.transform(scaled_samples)

# Print the shape of pca_features
print(pca_features.shape)
--------------------------------------------

----------------------------------------
TF-IDF 
-----------------------------------------

# Import TfidfVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer

# Create a TfidfVectorizer: tfidf
tfidf = TfidfVectorizer()

# Apply fit_transform to document: csr_mat
csr_mat = tfidf.fit_transform(documents)

# Print result of toarray() method
print(csr_mat.toarray())

# Get the words: got the words
words = tfidf.get_feature_names()

# Print words
print(words)



'''
Clustering Wikipedia part I
You saw in the video that TruncatedSVD is able to perform PCA on sparse arrays in csr_matrix format, such as word-frequency arrays. Combine your knowledge of TruncatedSVD and k-means to cluster some popular pages from Wikipedia. In this exercise, build the pipeline. In the next exercise, you'll apply it to the word-frequency array of some Wikipedia articles.

Create a Pipeline object consisting of a TruncatedSVD followed by KMeans. (This time, we've precomputed the word-frequency matrix for you, so there's no need for a TfidfVectorizer).
'''

# Perform the necessary imports
from sklearn.decomposition import TruncatedSVD
from sklearn.cluster import KMeans
from sklearn.pipeline import make_pipeline

# Create a TruncatedSVD instance: svd
svd = TruncatedSVD(n_components=50)

# Create a KMeans instance: kmeans
kmeans = KMeans(n_clusters=6)

# Create a pipeline: pipeline
pipeline = make_pipeline(svd,kmeans)


-------------------------------------------------
Non-Matrix Factorization 
--------------------------------------------------
# Import NMF
from sklearn.decomposition import NMF 

# Create an NMF instance: model
model = NMF(n_components=6)

# Fit the model to articles
model.fit(articles)

# Transform the articles: nmf_features
nmf_features = model.transform(articles)

# Print the NMF features
print(nmf_features) ## it reduces the columns from 1200 to 6 working best for the text data where there exists sparsity 
-------------------------------------------