Regression Techniques SImple Linear Regression

Clustering Techniques/Affinity-Propagation-Clustering-ALgorithm.py

@@ -0,0 +1,37 @@
+from numpy import unique
+from numpy import where
+from matplotlib import pyplot
+from sklearn.datasets import make_classification
+from sklearn.cluster import AffinityPropagation
+
+# initialize the data set we'll work with
+training_data, _ = make_classification(
+    n_samples=1000,
+    n_features=2,
+    n_informative=2,
+    n_redundant=0,
+    n_clusters_per_class=1,
+    random_state=4
+)
+
+# define the model
+model = AffinityPropagation(damping=0.7)
+
+# train the model
+model.fit(training_data)
+
+# assign each data point to a cluster
+result = model.predict(training_data)
+
+# get all of the unique clusters
+clusters = unique(result)
+
+# plot the clusters
+for cluster in clusters:
+    # get data points that fall in this cluster
+    index = where(result == cluster)
+    # make the plot
+    pyplot.scatter(training_data[index, 0], training_data[index, 1])
+
+# show the plot
+pyplot.show()

Clustering Techniques/Agglomerative-Clustering-Algorithm.py

@@ -0,0 +1,34 @@
+from numpy import unique
+from numpy import where
+from matplotlib import pyplot
+from sklearn.datasets import make_classification
+from sklearn.cluster import AgglomerativeClustering
+
+# initialize the data set we'll work with
+training_data, _ = make_classification(
+    n_samples=1000,
+    n_features=2,
+    n_informative=2,
+    n_redundant=0,
+    n_clusters_per_class=1,
+    random_state=4
+)
+
+# define the model
+agglomerative_model = AgglomerativeClustering(n_clusters=2)
+
+# assign each data point to a cluster
+agglomerative_result = agglomerative_model.fit_predict(training_data)
+
+# get all of the unique clusters
+agglomerative_clusters = unique(agglomerative_result)
+
+# plot the clusters
+for agglomerative_cluster in agglomerative_clusters:
+    # get data points that fall in this cluster
+    index = where(agglomerative_result == agglomerative_clusters)
+    # make the plot
+    pyplot.scatter(training_data[index, 0], training_data[index, 1])
+
+# show the Agglomerative Hierarchy plot
+pyplot.show()

Clustering Techniques/BIRCH-Algorithm.py

@@ -0,0 +1,37 @@
+from numpy import unique
+from numpy import where
+from matplotlib import pyplot
+from sklearn.datasets import make_classification
+from sklearn.cluster import Birch
+
+# initialize the data set we'll work with
+training_data, _ = make_classification(
+    n_samples=1000,
+    n_features=2,
+    n_informative=2,
+    n_redundant=0,
+    n_clusters_per_class=1,
+    random_state=4
+)
+
+# define the model
+birch_model = Birch(threshold=0.03, n_clusters=2)
+
+# train the model
+birch_model.fit(training_data)
+
+# assign each data point to a cluster
+birch_result = birch_model.predict(training_data)
+
+# get all of the unique clusters
+birch_clusters = unique(birch_result)
+
+# plot the BIRCH clusters
+for birch_cluster in birch_clusters:
+    # get data points that fall in this cluster
+    index = where(birch_result == birch_clusters)
+    # make the plot
+    pyplot.scatter(training_data[index, 0], training_data[index, 1])
+
+# show the BIRCH plot
+pyplot.show()

Clustering Techniques/DBSCAN-Model.py

@@ -0,0 +1,37 @@
+from numpy import unique
+from numpy import where
+from matplotlib import pyplot
+from sklearn.datasets import make_classification
+from sklearn.cluster import DBSCAN
+
+# initialize the data set we'll work with
+training_data, _ = make_classification(
+    n_samples=1000,
+    n_features=2,
+    n_informative=2,
+    n_redundant=0,
+    n_clusters_per_class=1,
+    random_state=4
+)
+
+# define the model
+dbscan_model = DBSCAN(eps=0.25, min_samples=9)
+
+# train the model
+dbscan_model.fit(training_data)
+
+# assign each data point to a cluster
+dbscan_result = dbscan_model.predict(training_data)
+
+# get all of the unique clusters
+dbscan_cluster = unique(dbscan_result)
+
+# plot the DBSCAN clusters
+for dbscan_cluster in dbscan_clusters:
+    # get data points that fall in this cluster
+    index = where(dbscan_result == dbscan_clusters)
+    # make the plot
+    pyplot.scatter(training_data[index, 0], training_data[index, 1])
+
+# show the DBSCAN plot
+pyplot.show()

Clustering Techniques/Gaussain-Mixture-Model.py

@@ -0,0 +1,37 @@
+from numpy import unique
+from numpy import where
+from matplotlib import pyplot
+from sklearn.datasets import make_classification
+from sklearn.mixture import GaussianMixture
+
+# initialize the data set we'll work with
+training_data, _ = make_classification(
+    n_samples=1000,
+    n_features=2,
+    n_informative=2,
+    n_redundant=0,
+    n_clusters_per_class=1,
+    random_state=4
+)
+
+# define the model
+gaussian_model = GaussianMixture(n_components=2)
+
+# train the model
+gaussian_model.fit(training_data)
+
+# assign each data point to a cluster
+gaussian_result = gaussian_model.predict(training_data)
+
+# get all of the unique clusters
+gaussian_clusters = unique(gaussian_result)
+
+# plot Gaussian Mixture the clusters
+for gaussian_cluster in gaussian_clusters:
+    # get data points that fall in this cluster
+    index = where(gaussian_result == gaussian_clusters)
+    # make the plot
+    pyplot.scatter(training_data[index, 0], training_data[index, 1])
+
+# show the Gaussian Mixture plot
+pyplot.show()

Clustering Techniques/Mean-Shift-Clustering-algorithm.py

@@ -0,0 +1,34 @@
+from numpy import unique
+from numpy import where
+from matplotlib import pyplot
+from sklearn.datasets import make_classification
+from sklearn.cluster import MeanShift
+
+# initialize the data set we'll work with
+training_data, _ = make_classification(
+    n_samples=1000,
+    n_features=2,
+    n_informative=2,
+    n_redundant=0,
+    n_clusters_per_class=1,
+    random_state=4
+)
+
+# define the model
+mean_model = MeanShift()
+
+# assign each data point to a cluster
+mean_result = mean_model.fit_predict(training_data)
+
+# get all of the unique clusters
+mean_clusters = unique(mean_result)
+
+# plot Mean-Shift the clusters
+for mean_cluster in mean_clusters:
+    # get data points that fall in this cluster
+    index = where(mean_result == mean_cluster)
+    # make the plot
+    pyplot.scatter(training_data[index, 0], training_data[index, 1])
+
+# show the Mean-Shift plot
+pyplot.show()

Clustering Techniques/OPTICS-algorithm.py

@@ -0,0 +1,34 @@
+from numpy import unique
+from numpy import where
+from matplotlib import pyplot
+from sklearn.datasets import make_classification
+from sklearn.cluster import OPTICS
+
+# initialize the data set we'll work with
+training_data, _ = make_classification(
+    n_samples=1000,
+    n_features=2,
+    n_informative=2,
+    n_redundant=0,
+    n_clusters_per_class=1,
+    random_state=4
+)
+
+# define the model
+optics_model = OPTICS(eps=0.75, min_samples=10)
+
+# assign each data point to a cluster
+optics_result = optics_model.fit_predict(training_data)
+
+# get all of the unique clusters
+optics_clusters = unique(optics_clusters)
+
+# plot OPTICS the clusters
+for optics_cluster in optics_clusters:
+    # get data points that fall in this cluster
+    index = where(optics_result == optics_clusters)
+    # make the plot
+    pyplot.scatter(training_data[index, 0], training_data[index, 1])
+
+# show the OPTICS plot
+pyplot.show()

Regression-Techniques/simple-linear-regression.py

@@ -0,0 +1,54 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+def estimate_coef(x, y):
+	# number of observations/points
+	n = np.size(x)
+
+	# mean of x and y vector
+	m_x = np.mean(x)
+	m_y = np.mean(y)
+
+	# calculating cross-deviation and deviation about x
+	SS_xy = np.sum(y*x) - n*m_y*m_x
+	SS_xx = np.sum(x*x) - n*m_x*m_x
+
+	# calculating regression coefficients
+	b_1 = SS_xy / SS_xx
+	b_0 = m_y - b_1*m_x
+
+	return (b_0, b_1)
+
+def plot_regression_line(x, y, b):
+	# plotting the actual points as scatter plot
+	plt.scatter(x, y, color = "m",
+			marker = "o", s = 30)
+
+	# predicted response vector
+	y_pred = b[0] + b[1]*x
+
+	# plotting the regression line
+	plt.plot(x, y_pred, color = "g")
+
+	# putting labels
+	plt.xlabel('x')
+	plt.ylabel('y')
+
+	# function to show plot
+	plt.show()
+
+def main():
+	# observations / data
+	x = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
+	y = np.array([1, 3, 2, 5, 7, 8, 8, 9, 10, 12])
+
+	# estimating coefficients
+	b = estimate_coef(x, y)
+	print("Estimated coefficients:\nb_0 = {} \
+		\nb_1 = {}".format(b[0], b[1]))
+
+	# plotting regression line
+	plot_regression_line(x, y, b)
+
+if __name__ == "__main__":
+	main()