Completion of Python files

Code/Day 11_k-NN.py

@@ -0,0 +1,31 @@
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('../datasets/Social_Network_Ads.csv')
+X = dataset.iloc[:, [2, 3]].values
+y = dataset.iloc[:, 4].values
+
+# Splitting the dataset into the Training set and Test set
+from sklearn.cross_validation import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
+
+# Feature Scaling
+from sklearn.preprocessing import StandardScaler
+sc = StandardScaler()
+X_train = sc.fit_transform(X_train)
+X_test = sc.transform(X_test)
+
+# Fitting K-NN to the Training set
+from sklearn.neighbors import KNeighborsClassifier
+classifier = KNeighborsClassifier(n_neighbors = 5, metric = 'minkowski', p = 2)
+classifier.fit(X_train, y_train)
+
+# Predicting the Test set results
+y_pred = classifier.predict(X_test)
+
+# Making the Confusion Matrix
+from sklearn.metrics import confusion_matrix
+cm = confusion_matrix(y_test, y_pred)

Code/Day 25_Decision_Tree.py

@@ -0,0 +1,68 @@
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('../datasets/Social_Network_Ads.csv')
+X = dataset.iloc[:, [2, 3]].values
+y = dataset.iloc[:, 4].values
+
+# Splitting the dataset into the Training set and Test set
+from sklearn.cross_validation import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
+
+# Feature Scaling
+from sklearn.preprocessing import StandardScaler
+sc = StandardScaler()
+X_train = sc.fit_transform(X_train)
+X_test = sc.transform(X_test)
+
+# Fitting Decision Tree Classification to the Training set
+from sklearn.tree import DecisionTreeClassifier
+classifier = DecisionTreeClassifier(criterion = 'entropy', random_state = 0)
+classifier.fit(X_train, y_train)
+
+# Predicting the Test set results
+y_pred = classifier.predict(X_test)
+
+# Making the Confusion Matrix
+from sklearn.metrics import confusion_matrix
+cm = confusion_matrix(y_test, y_pred)
+
+# Visualising the Training set results
+from matplotlib.colors import ListedColormap
+X_set, y_set = X_train, y_train
+X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
+                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
+plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
+             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
+plt.xlim(X1.min(), X1.max())
+plt.ylim(X2.min(), X2.max())
+for i, j in enumerate(np.unique(y_set)):
+    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
+                c = ListedColormap(('red', 'green'))(i), label = j)
+plt.title('Decision Tree Classification (Training set)')
+plt.xlabel('Age')
+plt.ylabel('Estimated Salary')
+plt.legend()
+plt.show()
+
+# Visualising the Test set results
+from matplotlib.colors import ListedColormap
+X_set, y_set = X_test, y_test
+X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
+                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
+plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
+             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
+plt.xlim(X1.min(), X1.max())
+plt.ylim(X2.min(), X2.max())
+for i, j in enumerate(np.unique(y_set)):
+    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
+                c = ListedColormap(('red', 'green'))(i), label = j)
+plt.title('Decision Tree Classification (Test set)')
+plt.xlabel('Age')
+plt.ylabel('Estimated Salary')
+plt.legend()
+plt.show()
+

Code/Day 2_Simple_Linear_Regression.py

@@ -0,0 +1,28 @@
+# Data Preprocessing
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+dataset = pd.read_csv('../datasets/studentscores.csv')
+X = dataset.iloc[ : ,   : 1 ].values
+Y = dataset.iloc[ : , 1 ].values
+
+from sklearn.cross_validation import train_test_split
+X_train, X_test, Y_train, Y_test = train_test_split( X, Y, test_size = 1/4, random_state = 0) 
+
+# Fitting Simple Linear Regression Model to the training set
+from sklearn.linear_model import LinearRegression
+regressor = LinearRegression()
+regressor = regressor.fit(X_train, Y_train)
+
+# Predecting the Result
+Y_pred = regressor.predict(X_test)
+
+# Visualising the Training results
+plt.scatter(X_train , Y_train, color = 'red')
+plt.plot(X_train , regressor.predict(X_train), color ='blue')
+
+# Visualizing the test results
+plt.scatter(X_test , Y_test, color = 'red')
+plt.plot(X_test , regressor.predict(X_test), color ='blue')
+

Code/Day 34_Random_Forests.py

@@ -0,0 +1,68 @@
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('../datasets/Social_Network_Ads.csv')
+X = dataset.iloc[:, [2, 3]].values
+y = dataset.iloc[:, 4].values
+
+# Splitting the dataset into the Training set and Test set
+from sklearn.cross_validation import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
+
+# Feature Scaling
+from sklearn.preprocessing import StandardScaler
+sc = StandardScaler()
+X_train = sc.fit_transform(X_train)
+X_test = sc.transform(X_test)
+
+# Fitting Random Forest to the Training set
+from sklearn.ensemble import RandomForestClassifier
+classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 0)
+classifier.fit(X_train, y_train)
+
+# Predicting the Test set results
+y_pred = classifier.predict(X_test)
+
+# Making the Confusion Matrix
+from sklearn.metrics import confusion_matrix
+cm = confusion_matrix(y_test, y_pred)
+
+# Visualising the Training set results
+from matplotlib.colors import ListedColormap
+X_set, y_set = X_train, y_train
+X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
+                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
+plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
+             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
+plt.xlim(X1.min(), X1.max())
+plt.ylim(X2.min(), X2.max())
+for i, j in enumerate(np.unique(y_set)):
+    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
+                c = ListedColormap(('red', 'green'))(i), label = j)
+plt.title('Random Forest Classification (Training set)')
+plt.xlabel('Age')
+plt.ylabel('Estimated Salary')
+plt.legend()
+plt.show()
+
+# Visualising the Test set results
+from matplotlib.colors import ListedColormap
+X_set, y_set = X_test, y_test
+X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
+                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
+plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
+             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
+plt.xlim(X1.min(), X1.max())
+plt.ylim(X2.min(), X2.max())
+for i, j in enumerate(np.unique(y_set)):
+    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
+                c = ListedColormap(('red', 'green'))(i), label = j)
+plt.title('Random Forest Classification (Test set)')
+plt.xlabel('Age')
+plt.ylabel('Estimated Salary')
+plt.legend()
+plt.show()
+

Code/Day 3_Multiple_Linear_Regression.py

@@ -0,0 +1,31 @@
+# Importing the libraries
+import pandas as pd
+import numpy as np
+
+# Importing the dataset
+dataset = pd.read_csv('../datasets/50_Startups.csv')
+X = dataset.iloc[ : , :-1].values
+Y = dataset.iloc[ : ,  4 ].values
+
+# Encoding Categorical data
+from sklearn.preprocessing import LabelEncoder, OneHotEncoder
+labelencoder = LabelEncoder()
+X[: , 3] = labelencoder.fit_transform(X[ : , 3])
+onehotencoder = OneHotEncoder(categorical_features = [3])
+X = onehotencoder.fit_transform(X).toarray()
+
+# Avoiding Dummy Variable Trap
+X = X[: , 1:]
+
+# Splitting the dataset into the Training set and Test set
+from sklearn.cross_validation import train_test_split
+X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state = 0)
+
+# Fitting Multiple Linear Regression to the Training set
+from sklearn.linear_model import LinearRegression
+regressor = LinearRegression()
+regressor.fit(X_train, Y_train)
+
+# Predicting the Test set results
+y_pred = regressor.predict(X_test)
+

Code/Day 6_Logistic_Regression.py

@@ -0,0 +1,32 @@
+# Importing the Libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('../datasets/Social_Network_Ads.csv')
+X = dataset.iloc[:, [2, 3]].values
+y = dataset.iloc[:, 4].values
+
+# Splitting the dataset into the Training set and Test set
+from sklearn.cross_validation import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
+
+# Feature Scaling
+from sklearn.preprocessing import StandardScaler
+sc = StandardScaler()
+X_train = sc.fit_transform(X_train)
+X_test = sc.transform(X_test)
+
+# Fitting Logistic Regression to the Training set
+from sklearn.linear_model import LogisticRegression
+classifier = LogisticRegression()
+classifier.fit(X_train, y_train)
+
+# Predicting the Test set results
+y_pred = classifier.predict(X_test)
+
+# Making the Confusion Matrix
+from sklearn.metrics import confusion_matrix
+cm = confusion_matrix(y_test, y_pred)
+