dim red with new examples

doc/src/DimRed/DimRed.do.txt

@@ -35,12 +35,114 @@ This scaling has the drawback that it does not ensure that we have a particular
 
 !eblock
 
+!split
+===== Simple preprocessing examples, Franke function and regression =====
+
+!bc pycod
+# Common imports
+import os
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import sklearn.linear_model as skl
+from sklearn.metrics import mean_squared_error
+from sklearn.model_selection import  train_test_split
+from sklearn.preprocessing import MinMaxScaler, StandardScaler, Normalizer
+from sklearn.svm import SVR
+
+# Where to save the figures and data files
+PROJECT_ROOT_DIR = "Results"
+FIGURE_ID = "Results/FigureFiles"
+DATA_ID = "DataFiles/"
+
+if not os.path.exists(PROJECT_ROOT_DIR):
+    os.mkdir(PROJECT_ROOT_DIR)
+
+if not os.path.exists(FIGURE_ID):
+    os.makedirs(FIGURE_ID)
+
+if not os.path.exists(DATA_ID):
+    os.makedirs(DATA_ID)
+
+def image_path(fig_id):
+    return os.path.join(FIGURE_ID, fig_id)
+
+def data_path(dat_id):
+    return os.path.join(DATA_ID, dat_id)
+
+def save_fig(fig_id):
+    plt.savefig(image_path(fig_id) + ".png", format='png')
+
+
+def FrankeFunction(x,y):
+	term1 = 0.75*np.exp(-(0.25*(9*x-2)**2) - 0.25*((9*y-2)**2))
+	term2 = 0.75*np.exp(-((9*x+1)**2)/49.0 - 0.1*(9*y+1))
+	term3 = 0.5*np.exp(-(9*x-7)**2/4.0 - 0.25*((9*y-3)**2))
+	term4 = -0.2*np.exp(-(9*x-4)**2 - (9*y-7)**2)
+	return term1 + term2 + term3 + term4
+
+
+def create_X(x, y, n ):
+	if len(x.shape) > 1:
+		x = np.ravel(x)
+		y = np.ravel(y)
+
+	N = len(x)
+	l = int((n+1)*(n+2)/2)		# Number of elements in beta
+	X = np.ones((N,l))
+
+	for i in range(1,n+1):
+		q = int((i)*(i+1)/2)
+		for k in range(i+1):
+			X[:,q+k] = (x**(i-k))*(y**k)
+
+	return X
+
+
+# Making meshgrid of datapoints and compute Franke's function
+n = 5
+N = 1000
+x = np.sort(np.random.uniform(0, 1, N))
+y = np.sort(np.random.uniform(0, 1, N))
+z = FrankeFunction(x, y)
+X = create_X(x, y, n=n)    
+# split in training and test data
+X_train, X_test, y_train, y_test = train_test_split(X,z,test_size=0.2)
+
+
+svm = SVR(gamma='auto',C=10.0)
+svm.fit(X_train, y_train)
+
+# The mean squared error and R2 score
+print("MSE before scaling: {:.2f}".format(mean_squared_error(svm.predict(X_test), y_test)))
+print("R2 score before scaling {:.2f}".format(svm.score(X_test,y_test)))
+
+scaler = StandardScaler()
+scaler.fit(X_train)
+X_train_scaled = scaler.transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+
+print("Feature min values before scaling:\n {}".format(X_train.min(axis=0)))
+print("Feature max values before scaling:\n {}".format(X_train.max(axis=0)))
+
+print("Feature min values after scaling:\n {}".format(X_train_scaled.min(axis=0)))
+print("Feature max values after scaling:\n {}".format(X_train_scaled.max(axis=0)))
+
+svm = SVR(gamma='auto',C=10.0)
+svm.fit(X_train_scaled, y_train)
+
+print("MSE after  scaling: {:.2f}".format(mean_squared_error(svm.predict(X_test_scaled), y_test)))
+print("R2 score for  scaled data: {:.2f}".format(svm.score(X_test_scaled,y_test)))
+
+!ec
+
+
 
 !split
-===== Simple preprocessing examples =====
+===== Simple preprocessing examples, breast cancer data and classification =====
+
+We show here how we can use a simple regression case on the breast cancer data using support vector machine as algorithm for classification
 
-We show here how we can use a simple regression case (our nuclear binding energies discussed earlier).
-Rescaling our data with different
 
 !bc pycod
 import matplotlib.pyplot as plt

doc/src/Regression/franke.py

@@ -7,6 +7,7 @@ import matplotlib.pyplot as plt
 import sklearn.linear_model as skl
 from sklearn.metrics import mean_squared_error
 from sklearn.model_selection import  train_test_split
+from sklearn.preprocessing import MinMaxScaler, StandardScaler, Normalizer
 from sklearn.svm import SVR
 
 # Where to save the figures and data files
@@ -41,7 +42,7 @@ def FrankeFunction(x,y):
 	return term1 + term2 + term3 + term4
 
 
-def create_X(x, y, n = 5):
+def create_X(x, y, n ):
 	if len(x.shape) > 1:
 		x = np.ravel(x)
 		y = np.ravel(y)
@@ -71,14 +72,11 @@ X_train, X_test, y_train, y_test = train_test_split(X,z,test_size=0.2)
 svm = SVR(gamma='auto',C=10.0)
 svm.fit(X_train, y_train)
 
-# The mean squared error                               
-print("Test set accuracy: {:.2f}".format(svm.score(X_test,y_test)))
+# The mean squared error and R2 score
+print("MSE before scaling: {:.2f}".format(mean_squared_error(svm.predict(X_test), y_test)))
+print("R2 score before scaling {:.2f}".format(svm.score(X_test,y_test)))
 
 
-
-
-from sklearn.preprocessing import MinMaxScaler, StandardScaler
-
 scaler = StandardScaler()
 scaler.fit(X_train)
 X_train_scaled = scaler.transform(X_train)
@@ -95,7 +93,7 @@ print("Feature max values after scaling:\n {}".format(X_train_scaled.max(axis=0)
 svm = SVR(gamma='auto',C=10.0)
 svm.fit(X_train_scaled, y_train)
 
-
+print("MSE after  scaling: {:.2f}".format(mean_squared_error(svm.predict(X_test_scaled), y_test)))
 print("Test set accuracy scaled data: {:.2f}".format(svm.score(X_test_scaled,y_test)))