add files

03Handing Numrical data/00Problem.py

@@ -0,0 +1,20 @@
+# ReScaling a feature
+
+# Load the Library
+import numpy as np
+from sklearn import preprocessing
+
+# Create Feature
+feature = np.array([[-900.5],
+                    [-300.1],
+                    [0],
+                    [300.1],
+                    [900.9]])
+
+# Create Scaler
+minmax_Scale = preprocessing.MinMaxScaler(feature_range=(0, 1))
+# Scale feature
+scaled_feature = minmax_Scale.fit_transform(feature)
+
+# show feature
+print(scaled_feature)

03Handing Numrical data/01Problem.py

@@ -0,0 +1,40 @@
+# Standardizing a Feature
+
+# Load the Libraries
+import numpy as np
+from sklearn.preprocessing import *
+
+# Create feature
+x = np.array([[-1000.1],
+              [-200.2],
+              [500.3],
+              [600.6],
+              [9000.9]])
+
+# Create Feature
+scaler = StandardScaler()
+
+# Transform the feature
+standardized = scaler.fit_transform(x)
+
+# show the feature
+print(standardized)
+
+# print mean and std
+print('mean :', round(standardized.mean()))
+print('Std', standardized.std())
+
+
+'''
+If our data has significant outliers, it can negatively impact our standardization by
+affecting the feature’s mean and variance. In this scenario, it is often helpful to instead
+rescale the feature using the median and quartile range. In scikit-learn, we do this
+using the RobustScaler method
+'''
+# Create scaler
+robust_scaler = RobustScaler()
+
+# Transform Feature
+tf = robust_scaler.fit_transform(x)
+# show the feature
+print(tf)

03Handing Numrical data/02Problem.py

@@ -0,0 +1,34 @@
+# Normalizing Observation
+
+# Load the libraries
+import numpy as np
+from sklearn.preprocessing import Normalizer
+
+# Crate a featture matrix
+features = np.array([[0.5, 0.5],
+                    [1.1, 3.5],
+                    [1.5, 20.2],
+                    [1.64, 34.5],
+                    [10.9, 3.3]])
+
+# create normalizer
+normalizer = Normalizer(norm='l2')
+
+'''
+s. Normalizer
+rescales the values on individual observations to have unit norm (the sum of their
+lengths is 1). This type of rescaling is often used when we have many equivalent fea‐
+tures (e.g., text classification when every word or n-word group is a feature).
+'''
+# Transform feature matrix
+print(normalizer.transform(features))
+
+'''
+Normalizer provides three norm options with
+Euclidean norm (often called L2)
+
+'''
+
+# Transform feature matrix
+f_l1_norm = Normalizer(norm='l1').transform(features)
+print(f_l1_norm)