AI－常见机器学习算法介绍_ai机器学习

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

#Import Library

#Import other necessary libraries like pandas, numpy...

from  sklearn  import  linear_model

#Load Train and Test datasets

#Identify feature and response variable(s) and values must be numeric and numpy arrays

x_train = input_variables_values_training_datasets

y_train = target_variables_values_training_datasets

x_test = input_variables_values_test_datasets

# Create linear regression object

linear  =  linear_model.LinearRegression()

# Train the model using the training sets and check score

linear.fit(x_train, y_train)

linear.score(x_train, y_train)

#Equation coefficient and Intercept

print ( 'Coefficient: n' , linear.coef_)

print ( 'Intercept: n' , linear.intercept_)

#Predict Output

predicted =  linear.predict(x_test)

1

2

3

4

5

6

7

8

9

10

11

12

13

#Load Train and Test datasets

#Identify feature and response variable(s) and values must be numeric and numpy arrays

x_train <- input_variables_values_training_datasets

y_train <- target_variables_values_training_datasets

x_test <- input_variables_values_test_datasets

x <- cbind(x_train,y_train)

# Train the model using the training sets and check score

linear <- lm(y_train ~ ., data = x)

summary(linear)

#Predict Output

predicted= predict(linear,x_test)

1

2

3

odds= p/ (1-p) = probability of event occurrence / probability of not event occurrence

ln(odds) = ln(p/(1-p))

logit(p) = ln(p/(1-p)) = b0+b1X1+b2X2+b3X3....+bkXk

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

#Import Library

from  sklearn.linear_model  import  LogisticRegression

#Assumed you have, X (predictor) and Y (target) for training data set and x_test(predictor) of test_dataset

# Create logistic regression object

model  =  LogisticRegression()

# Train the model using the training sets and check score

model.fit(X, y)

model.score(X, y)

#Equation coefficient and Intercept

print ( 'Coefficient: n' , model.coef_)

print ( 'Intercept: n' , model.intercept_)

#Predict Output

predicted =  model.predict(x_test)

1

2

3

4

5

6

7

x <- cbind(x_train,y_train)

# Train the model using the training sets and check score

logistic <- glm(y_train ~ ., data = x,family='binomial')

summary(logistic)

#Predict Output

predicted= predict(logistic,x_test)

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

#Import Library

#Import other necessary libraries like pandas, numpy...

from  sklearn  import  tree

#Assumed you have, X (predictor) and Y (target) for training data set and x_test(predictor) of test_dataset

# Create tree object

model  =  tree.DecisionTreeClassifier(criterion = 'gini' )  # for classification, here you can change the algorithm as gini or entropy (information gain) by default it is gini 

# model = tree.DecisionTreeRegressor() for regression

# Train the model using the training sets and check score

model.fit(X, y)

model.score(X, y)

#Predict Output

predicted =  model.predict(x_test)

1

2

3

4

5

6

7

8

9

library(rpart)

x <- cbind(x_train,y_train)

# grow tree 

fit <- rpart(y_train ~ ., data = x,method="class")

summary(fit)

#Predict Output 

predicted= predict(fit,x_test)

1

2

3

4

5

6

7

8

9

10

11

12

13

#Import Library

from  sklearn  import  svm

#Assumed you have, X (predic

tor)  and  Y (target)  for  training data  set  and  x_test(predictor) of test_dataset

# Create SVM classification object

model  =  svm.svc()  # there is various option associated with it, this is simple for classification. You can refer link, for mo# re detail.

# Train the model using the training sets and check score

model.fit(X, y)

model.score(X, y)

#Predict Output

predicted =  model.predict(x_test)

1

2

3

4

5

6

7

8

9

library(e1071)

x <- cbind(x_train,y_train)

# Fitting model

fit <-svm(y_train ~ ., data = x)

summary(fit)

#Predict Output 

predicted= predict(fit,x_test)

1

2

3

4

5

6

7

8

9

10

#Import Library

from  sklearn.naive_bayes  import  GaussianNB

#Assumed you have, X (predictor) and Y (target) for training data set and x_test(predictor) of test_dataset

# Create SVM classification object model = GaussianNB() # there is other distribution for multinomial classes like Bernoulli Naive Bayes, Refer link

# Train the model using the training sets and check score

model.fit(X, y)

#Predict Output

predicted =  model.predict(x_test)

1

2

3

4

5

6

7

8

9

library(e1071)

x <- cbind(x_train,y_train)

# Fitting model

fit <-naiveBayes(y_train ~ ., data = x)

summary(fit)

#Predict Output 

predicted= predict(fit,x_test)

1

2

3

4

5

6

7

8

9

10

11

12

#Import Library

from  sklearn.neighbors  import  KNeighborsClassifier

#Assumed you have, X (predictor) and Y (target) for training data set and x_test(predictor) of test_dataset

# Create KNeighbors classifier object model

KNeighborsClassifier(n_neighbors = 6 )  # default value for n_neighbors is 5

# Train the model using the training sets and check score

model.fit(X, y)

#Predict Output

predicted =  model.predict(x_test)

1

2

3

4

5

6

7

8

9

library(knn)

x <- cbind(x_train,y_train)

# Fitting model

fit <-knn(y_train ~ ., data = x,k=5)

summary(fit)

#Predict Output 

predicted= predict(fit,x_test)

1

2

3

4

5

6

7

8

9

10

11

12

#Import Library

from  sklearn.cluster  import  KMeans

#Assumed you have, X (attributes) for training data set and x_test(attributes) of test_dataset

# Create KNeighbors classifier object model

k_means  =  KMeans(n_clusters = 3 , random_state = 0 )

# Train the model using the training sets and check score

model.fit(X)

#Predict Output

predicted =  model.predict(x_test)

1

2

library(cluster)

fit <- kmeans(X, 3) # 5 cluster solution

1

2

3

4

5

6

7

8

9

10

11

12

#Import Library

from  sklearn.ensemble  import  RandomForestClassifier

#Assumed you have, X (predictor) and Y (target) for training data set and x_test(predictor) of test_dataset

# Create Random Forest object

model =  RandomForestClassifier()

# Train the model using the training sets and check score

model.fit(X, y)

#Predict Output

predicted =  model.predict(x_test)

1

2

3

4

5

6

7

8

9

library(randomForest)

x <- cbind(x_train,y_train)

# Fitting model

fit <- randomForest(Species ~ ., x,ntree=500)

summary(fit)

#Predict Output 

predicted= predict(fit,x_test)

1

2

3

4

5

6

7

8

9

10

11

12

13

14

#Import Library

from  sklearn  import  decomposition

#Assumed you have training and test data set as train and test

# Create PCA obeject pca= decomposition.PCA(n_components=k) #default value of k =min(n_sample, n_features)

# For Factor analysis

#fa= decomposition.FactorAnalysis()

# Reduced the dimension of training dataset using PCA

train_reduced  =  pca.fit_transform(train)

#Reduced the dimension of test dataset

test_reduced  =  pca.transform(test)

#For more detail on this, please refer  this link.

1

2

3

4

library(stats)

pca <- princomp(train, cor = TRUE)

train_reduced  <- predict(pca,train)

test_reduced  <- predict(pca,test)

1

2

3

4

5

6

7

8

9

10

11

12

#Import Library

from  sklearn.ensemble  import  GradientBoostingClassifier

#Assumed you have, X (predictor) and Y (target) for training data set and x_test(predictor) of test_dataset

# Create Gradient Boosting Classifier object

model =  GradientBoostingClassifier(n_estimators = 100 , learning_rate = 1.0 , max_depth = 1 , random_state = 0 )

# Train the model using the training sets and check score

model.fit(X, y)

#Predict Output

predicted =  model.predict(x_test)

1

2

3

4

5

6

7

library(caret)

x <- cbind(x_train,y_train)

# Fitting model

fitControl <- trainControl( method = "repeatedcv", number = 4, repeats = 4)

fit <- train(y ~ ., data = x, method = "gbm", trControl = fitControl,verbose = FALSE)

predicted= predict(fit,x_test,type= "prob")[,2]