Added the files taught in the earlier videos of the course Machine Learning Recipes.

Decision-Tree(flowers).py

@@ -0,0 +1,19 @@
+from sklearn.datasets import load_iris
+import numpy as np
+from sklearn import tree
+from sklearn.metrics import accuracy_score
+
+iris = load_iris()
+
+test_index = [0,50,100]
+train_target = np.delete(iris.target,test_index)
+train_data = np.delete(iris.data,test_index, axis=0)
+
+test_target = iris.target[test_index]
+test_data = iris.data[test_index]
+
+clf = tree.DecisionTreeClassifier()
+clf.fit(train_data,train_target)
+pred = clf.predict(test_data)
+
+print(accuracy_score(test_target,pred))

Decision-Tree(fruits).py

@@ -0,0 +1,7 @@
+from sklearn import tree
+features = [[140,0],[130,0],[150,1],[170,1]] 
+labels = [0,0,1,1]
+clf = tree.DecisionTreeClassifier()
+clf = clf.fit(features,labels)
+print(clf.predict([[120,0]])) #Output 0
+print(clf.predict([[180,1]])) #Output 1

KNeighbors(flowers).py

@@ -0,0 +1,17 @@
+from sklearn import datasets
+from sklearn.cross_validation import train_test_split
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.metrics import accuracy_score
+
+iris = datasets.load_iris()
+x = iris.data
+y = iris.target
+
+x_train,x_test,y_train,y_test = train_test_split(x,y,test_size = 0.5)
+
+clf = KNeighborsClassifier()
+clf.fit(x_train,y_train)
+
+predictions = clf.predict(x_test)
+
+print(accuracy_score(y_test,predictions))

Scrappy_KNN.py

@@ -0,0 +1,43 @@
+#Simple but relatively slow since it has to iterate over every data-point.
+
+import random
+from scipy.spatial import distance
+from sklearn.datasets import load_iris
+import numpy as np
+from sklearn.model_selection import train_test_split 
+from sklearn.metrics import accuracy_score
+
+def euc(a,b):
+  return(distance.euclidean(a,b))
+
+class Classifier():
+
+  def fit(self,train,train_labels):
+    self.train = train
+    self.train_labels = train_labels
+
+  def closest(self,x):
+    best_dist=euc(x,self.train[0])
+    best_index = 0 
+    for i in range(len(self.train)):
+      dist=euc(x,self.train[i])
+      if(dist<best_dist):
+        best_dist=dist
+        best_index=i
+    return(self.train_labels[best_index])
+
+  def predict(self,test):
+    predictions = []
+    for i in test:
+      label = self.closest(i)
+      predictions.append(label)
+    return(predictions)
+
+iris = load_iris()
+features = iris.data
+labels = iris.target
+train,test,train_labels,test_labels = train_test_split(features,labels,test_size=0.5)
+classifier = Classifier()
+classifier.fit(train,train_labels)
+pred = classifier.predict(test)
+print(accuracy_score(test_labels,pred))

Understanding_Features.py

@@ -0,0 +1,11 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+greyhounds = 500
+labs = 500
+
+grey_height = 28+4*np.random.randn(greyhounds)
+lab_height = 24+4*np.random.randn(labs)
+
+plt.hist([grey_height,lab_height],stacked = True, color = ['r','b'])
+plt.show()