first commit

Part 1 - Data Preprocessing/Data.csv

@@ -0,0 +1,11 @@
+Country,Age,Salary,Purchased
+France,44,72000,No
+Spain,27,48000,Yes
+Germany,30,54000,No
+Spain,38,61000,No
+Germany,40,,Yes
+France,35,58000,Yes
+Spain,,52000,No
+France,48,79000,Yes
+Germany,50,83000,No
+France,37,67000,Yes

Part 1 - Data Preprocessing/categorical_data.R

@@ -0,0 +1,20 @@
+# Data Preprocessing
+
+# Importing the dataset
+dataset = read.csv('Data.csv')
+
+# Taking care of missing data
+dataset$Age = ifelse(is.na(dataset$Age),
+                     ave(dataset$Age, FUN = function(x) mean(x, na.rm = TRUE)),
+                     dataset$Age)
+dataset$Salary = ifelse(is.na(dataset$Salary),
+                        ave(dataset$Salary, FUN = function(x) mean(x, na.rm = TRUE)),
+                        dataset$Salary)
+
+# Encoding categorical data
+dataset$Country = factor(dataset$Country,
+                         levels = c('France', 'Spain', 'Germany'),
+                         labels = c(1, 2, 3))
+dataset$Purchased = factor(dataset$Purchased,
+                           levels = c('No', 'Yes'),
+                           labels = c(0, 1))

Part 1 - Data Preprocessing/categorical_data.py

@@ -0,0 +1,28 @@
+# Data Preprocessing
+
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('Data.csv')
+X = dataset.iloc[:, :-1].values
+y = dataset.iloc[:, 3].values
+
+# Taking care of missing data
+from sklearn.preprocessing import Imputer
+imputer = Imputer(missing_values = 'NaN', strategy = 'mean', axis = 0)
+imputer = imputer.fit(X[:, 1:3])
+X[:, 1:3] = imputer.transform(X[:, 1:3])
+
+# Encoding categorical data
+# Encoding the Independent Variable
+from sklearn.preprocessing import LabelEncoder, OneHotEncoder
+labelencoder_X = LabelEncoder()
+X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
+onehotencoder = OneHotEncoder(categorical_features = [0])
+X = onehotencoder.fit_transform(X).toarray()
+# Encoding the Dependent Variable
+labelencoder_y = LabelEncoder()
+y = labelencoder_y.fit_transform(y)

Part 1 - Data Preprocessing/data_preprocessing.py

@@ -0,0 +1,40 @@
+# Data Preprocessing Template
+
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('Data.csv')
+X = dataset.iloc[:, :-1].values
+y = dataset.iloc[:, 3].values
+
+#Take care of misssing data
+from sklearn.preprocessing import Imputer
+imputer=Imputer(missing_values="NaN", strategy="mean", axis=0)
+imputer = imputer.fit(X[:, 1:3])
+X[:,1:3]=imputer.transform(X[:,1:3])
+
+
+#Encoding Categorical data
+from sklearn.preprocessing import OneHotEncoder, LabelEncoder
+labelencoder_x = LabelEncoder()
+X[:,0] = labelencoder_x.fit_transform(X[:,0])
+onehotencoder = OneHotEncoder(categorical_features=[0])
+X = onehotencoder.fit_transform(X).toarray()
+
+labelencoder_y = LabelEncoder()
+y = labelencoder_y.fit_transform(y)
+
+# Splitting the dataset into the Training set and Test set
+from sklearn.model_selection import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
+
+# Feature Scaling
+from sklearn.preprocessing import StandardScaler
+sc_X = StandardScaler()
+X_train = sc_X.fit_transform(X_train)
+X_test = sc_X.transform(X_test)
+sc_y = StandardScaler()
+y_train = sc_y.fit_transform(y_train)

Part 1 - Data Preprocessing/data_preprocessing_template.R

@@ -0,0 +1,16 @@
+# Data Preprocessing Template
+
+# Importing the dataset
+dataset = read.csv('Data.csv')
+
+# Splitting the dataset into the Training set and Test set
+# install.packages('caTools')
+library(caTools)
+set.seed(123)
+split = sample.split(dataset$DependentVariable, SplitRatio = 0.8)
+training_set = subset(dataset, split == TRUE)
+test_set = subset(dataset, split == FALSE)
+
+# Feature Scaling
+# training_set = scale(training_set)
+# test_set = scale(test_set)

Part 1 - Data Preprocessing/missing_data.R

@@ -0,0 +1,12 @@
+# Data Preprocessing
+
+# Importing the dataset
+dataset = read.csv('Data.csv')
+
+# Taking care of missing data
+dataset$Age = ifelse(is.na(dataset$Age),
+                     ave(dataset$Age, FUN = function(x) mean(x, na.rm = TRUE)),
+                     dataset$Age)
+dataset$Salary = ifelse(is.na(dataset$Salary),
+                        ave(dataset$Salary, FUN = function(x) mean(x, na.rm = TRUE)),
+                        dataset$Salary)

Part 1 - Data Preprocessing/missing_data.py

@@ -0,0 +1,17 @@
+# Data Preprocessing
+
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('Data.csv')
+X = dataset.iloc[:, :-1].values
+y = dataset.iloc[:, 3].values
+
+# Taking care of missing data
+from sklearn.preprocessing import Imputer
+imputer = Imputer(missing_values = 'NaN', strategy = 'mean', axis = 0)
+imputer = imputer.fit(X[:, 1:3])
+X[:, 1:3] = imputer.transform(X[:, 1:3])

Part 2 - Regression/Section 4 - Simple Linear Regression/Salary_Data.csv

@@ -0,0 +1,31 @@
+YearsExperience,Salary
+1.1,39343.00
+1.3,46205.00
+1.5,37731.00
+2.0,43525.00
+2.2,39891.00
+2.9,56642.00
+3.0,60150.00
+3.2,54445.00
+3.2,64445.00
+3.7,57189.00
+3.9,63218.00
+4.0,55794.00
+4.0,56957.00
+4.1,57081.00
+4.5,61111.00
+4.9,67938.00
+5.1,66029.00
+5.3,83088.00
+5.9,81363.00
+6.0,93940.00
+6.8,91738.00
+7.1,98273.00
+7.9,101302.00
+8.2,113812.00
+8.7,109431.00
+9.0,105582.00
+9.5,116969.00
+9.6,112635.00
+10.3,122391.00
+10.5,121872.00

Part 2 - Regression/Section 4 - Simple Linear Regression/simple_linear_regression.py

@@ -0,0 +1,28 @@
+#Simple Linear Regression
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('Salary_Data.csv')
+X = dataset.iloc[:, :-1].values
+y = dataset.iloc[:, 1].values
+
+from sklearn.model_selection import train_test_split
+X_train,X_test, y_train, y_test=train_test_split(X,y,test_size=1/3, random_state=0)
+
+#Fittin Simple Linear Regression
+from sklearn.linear_model import LinearRegression
+regressor = LinearRegression()
+regressor.fit(X_train, y_train)
+
+#Predicting the results
+y_pred = regressor.predict(X_test)
+
+#Visualizing the predictions
+plt.scatter(X_train,y_train, color='red')
+plt.plot(X_train, regressor.predict(X_train), color='blue')
+plt.title('Salary vs Experience (Training set)')
+plt.xlabel('Years of Experience')
+plt.ylabel('Salary')
+plt.show()

Part 2 - Regression/Section 5 - Multiple Linear Regression/50_Startups.csv

@@ -0,0 +1,51 @@
+R&D Spend,Administration,Marketing Spend,State,Profit
+165349.2,136897.8,471784.1,New York,192261.83
+162597.7,151377.59,443898.53,California,191792.06
+153441.51,101145.55,407934.54,Florida,191050.39
+144372.41,118671.85,383199.62,New York,182901.99
+142107.34,91391.77,366168.42,Florida,166187.94
+131876.9,99814.71,362861.36,New York,156991.12
+134615.46,147198.87,127716.82,California,156122.51
+130298.13,145530.06,323876.68,Florida,155752.6
+120542.52,148718.95,311613.29,New York,152211.77
+123334.88,108679.17,304981.62,California,149759.96
+101913.08,110594.11,229160.95,Florida,146121.95
+100671.96,91790.61,249744.55,California,144259.4
+93863.75,127320.38,249839.44,Florida,141585.52
+91992.39,135495.07,252664.93,California,134307.35
+119943.24,156547.42,256512.92,Florida,132602.65
+114523.61,122616.84,261776.23,New York,129917.04
+78013.11,121597.55,264346.06,California,126992.93
+94657.16,145077.58,282574.31,New York,125370.37
+91749.16,114175.79,294919.57,Florida,124266.9
+86419.7,153514.11,0,New York,122776.86
+76253.86,113867.3,298664.47,California,118474.03
+78389.47,153773.43,299737.29,New York,111313.02
+73994.56,122782.75,303319.26,Florida,110352.25
+67532.53,105751.03,304768.73,Florida,108733.99
+77044.01,99281.34,140574.81,New York,108552.04
+64664.71,139553.16,137962.62,California,107404.34
+75328.87,144135.98,134050.07,Florida,105733.54
+72107.6,127864.55,353183.81,New York,105008.31
+66051.52,182645.56,118148.2,Florida,103282.38
+65605.48,153032.06,107138.38,New York,101004.64
+61994.48,115641.28,91131.24,Florida,99937.59
+61136.38,152701.92,88218.23,New York,97483.56
+63408.86,129219.61,46085.25,California,97427.84
+55493.95,103057.49,214634.81,Florida,96778.92
+46426.07,157693.92,210797.67,California,96712.8
+46014.02,85047.44,205517.64,New York,96479.51
+28663.76,127056.21,201126.82,Florida,90708.19
+44069.95,51283.14,197029.42,California,89949.14
+20229.59,65947.93,185265.1,New York,81229.06
+38558.51,82982.09,174999.3,California,81005.76
+28754.33,118546.05,172795.67,California,78239.91
+27892.92,84710.77,164470.71,Florida,77798.83
+23640.93,96189.63,148001.11,California,71498.49
+15505.73,127382.3,35534.17,New York,69758.98
+22177.74,154806.14,28334.72,California,65200.33
+1000.23,124153.04,1903.93,New York,64926.08
+1315.46,115816.21,297114.46,Florida,49490.75
+0,135426.92,0,California,42559.73
+542.05,51743.15,0,New York,35673.41
+0,116983.8,45173.06,California,14681.4

Part 2 - Regression/Section 5 - Multiple Linear Regression/Multiple_Linear_Regression/Multiple_Linear_Regression/data_preprocessing_template.R

@@ -0,0 +1,16 @@
+# Data Preprocessing Template
+
+# Importing the dataset
+dataset = read.csv('Data.csv')
+
+# Splitting the dataset into the Training set and Test set
+# install.packages('caTools')
+library(caTools)
+set.seed(123)
+split = sample.split(dataset$DependentVariable, SplitRatio = 0.8)
+training_set = subset(dataset, split == TRUE)
+test_set = subset(dataset, split == FALSE)
+
+# Feature Scaling
+# training_set = scale(training_set)
+# test_set = scale(test_set)

Part 2 - Regression/Section 5 - Multiple Linear Regression/Multiple_Linear_Regression/Multiple_Linear_Regression/data_preprocessing_template.py

@@ -0,0 +1,23 @@
+# Data Preprocessing Template
+
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('Data.csv')
+X = dataset.iloc[:, :-1].values
+y = dataset.iloc[:, 3].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 = 0.2, random_state = 0)
+
+# Feature Scaling
+"""from sklearn.preprocessing import StandardScaler
+sc_X = StandardScaler()
+X_train = sc_X.fit_transform(X_train)
+X_test = sc_X.transform(X_test)
+sc_y = StandardScaler()
+y_train = sc_y.fit_transform(y_train)"""

Part 2 - Regression/Section 5 - Multiple Linear Regression/Multiple_Linear_Regression/Multiple_Linear_Regression/multiple_linear_regression.R

@@ -0,0 +1,28 @@
+# Multiple Linear Regression
+
+# Importing the dataset
+dataset = read.csv('50_Startups.csv')
+
+# Encoding categorical data
+dataset$State = factor(dataset$State,
+                       levels = c('New York', 'California', 'Florida'),
+                       labels = c(1, 2, 3))
+
+# Splitting the dataset into the Training set and Test set
+# install.packages('caTools')
+library(caTools)
+set.seed(123)
+split = sample.split(dataset$Profit, SplitRatio = 0.8)
+training_set = subset(dataset, split == TRUE)
+test_set = subset(dataset, split == FALSE)
+
+# Feature Scaling
+# training_set = scale(training_set)
+# test_set = scale(test_set)
+
+# Fitting Multiple Linear Regression to the Training set
+regressor = lm(formula = Profit ~ .,
+               data = training_set)
+
+# Predicting the Test set results
+y_pred = predict(regressor, newdata = test_set)

Part 2 - Regression/Section 5 - Multiple Linear Regression/Multiple_Linear_Regression/Multiple_Linear_Regression/multiple_linear_regression.py

@@ -0,0 +1,41 @@
+# Multiple Linear Regression
+
+# Importing the libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('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 the 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)
+
+# Feature Scaling
+"""from sklearn.preprocessing import StandardScaler
+sc_X = StandardScaler()
+X_train = sc_X.fit_transform(X_train)
+X_test = sc_X.transform(X_test)
+sc_y = StandardScaler()
+y_train = sc_y.fit_transform(y_train)"""
+
+# 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)