Korada Pavan Kumar_190108028

Phase 3 - 2020 (Summer)/Week 1 (Mar 28 - Apr 4)/Korada Pavan Kumar_190108028/Bonus/Code_PCA.py

@@ -0,0 +1,64 @@
+
+
+from matplotlib import pyplot as plt                
+import pandas as pd
+from sklearn.decomposition import PCA
+from sklearn.preprocessing import StandardScaler
+
+
+# Code is written to find out the pca graph of ten dimensional data given 
+
+df = pd.read_csv('data.txt',delimiter='\t', names=['Label', 'F1', 'F2', 'F3', 'F4', 'F5', 'F6', 'F7', 'F8', 'F9', 'F10'])
+
+features = ['F1', 'F2', 'F3', 'F4', 'F5', 'F6', 'F7', 'F8', 'F9', 'F10']
+x =df.loc[:, features].values
+y = df.loc[:, ['Label']].values
+x = StandardScaler().fit_transform(x)
+#print(pd.DataFrame(data = x, columns = features).head())
+
+pca = PCA(n_components =2)
+principalComponents = pca.fit_transform(x)
+principalDf =pd.DataFrame(data = principalComponents
+                          , columns =['principal component 1','principal component 2'])
+
+print(principalDf.head(5))
+print(df[['Label']].head())
+
+finalDf = pd.concat([principalDf , df[['Label']]], axis = 1)
+print(finalDf.head(1000))
+
+fig =plt.figure(figsize =(8,8))
+ax = fig.add_subplot(1,1,1)
+ax.set_xlabel('Principal Component 1', fontsize = 15)
+ax.set_ylabel('Principal Component 2', fontsize = 15)
+ax.set_title('2 Component PCA', fontsize = 20)
+
+targets =[ 1, 2]
+colors = ['r', 'g', 'b']
+for target, color in zip(targets, colors):
+    indicesToKeep = finalDf['Label'] == target
+    ax.scatter(finalDf.loc[indicesToKeep, 'principal component 1']
+               , finalDf.loc[indicesToKeep, 'principal component 2']
+               , c = color
+               , s= 50)
+
+ax.legend(targets)
+ax.grid()
+
+
+print(pca.explained_variance_ratio_)
+
+
+# General variance ratio >= 85%; here it is very much less(approx40) than that which 
+ # indicates that so much of information is lost; so what I infer is that 
+ # principal components chosen should be more than '2'
+
+
+
+
+"""
+Created on Sun Apr  5 08:04:06 2020
+
+@author: mailm
+"""
+

Phase 3 - 2020 (Summer)/Week 1 (Mar 28 - Apr 4)/Korada Pavan Kumar_190108028/Code_Week1.py

@@ -0,0 +1,42 @@
+import numpy as np
+#from matplotlib import pyplot as plt                # For plots only
+data_array = np.loadtxt('data.txt', delimiter='\t', skiprows=1)
+
+list_lab1 = []                                       # empty list for label 1
+list_lab2 = []                                       # empty list for label 2
+
+
+
+for i in range(999):                             # Random variable i
+    if( data_array[i, 0]==1):
+        list_lab1.append(data_array[i, 1:])
+    else:
+        list_lab2.append(data_array[i, 1:])
+
+array_lab1 = np.array(list_lab1)                    # Required array of data of label 1
+array_lab2 = np.array(list_lab2)                    # Required array of data of label 2
+
+
+print(array_lab1)
+print(array_lab2)
+"""
+#For the plots
+for x in range(0,10):                              # For some random variable x and y
+    for y in range(x, 10):
+         if x != y :
+             plt.title('Feature {} vs {}'.format(x, y))
+             plt.scatter(array_lab1[:, x], array_lab1[:, y], color ='r', label='Label 1')
+             plt.scatter(array_lab2[:, x], array_lab2[:, y], color ='b', label='Label 2')
+             plt.xlabel('Feature {}'.format(x))
+             plt.ylabel('Feature {}'.format(y))
+             plt.legend()
+             plt.show()
+"""
+
+
+
+"""
+Created on Sun Apr  2 01:05:21 2020
+
+@author: mailm
+"""

Phase 3 - 2020 (Summer)/Week 1 (Mar 28 - Apr 4)/Korada Pavan Kumar_190108028/Part3_Ans.txt

@@ -0,0 +1 @@
+Feature 1 vs 2 (Figure_1) is the best graph which differentiaites the two labels.