Machine learning

Suprevised

Regression

Classification

Linear Regression

from sklearn.linear_model import LinearRegression
LR = LinerRegression()
LR.fit(x_train, ytrain)
LR.coef
LR.intercept_

predictions = LR.predict(your_x_data)
prediction.score(x,y) : gives R2

Naive Bayes

from sklearn.naive_bayes import MultinomialNB
your_model = MultinomialNB()
your_model.fit(x_training_data, y_training_data)

predictions = your_model.predict(your_x_data)
probabilities = your_model.predict_proba(your_x_data)

K-Nearest Neighbors

from sklearn.neigbors import KNeighborsClassifier
your_model = KNeighborsClassifier()
your_model.fit(x_training_data, y_training_data)

predictions = your_model.predict(your_x_data)
probabilities = your_model.predict_proba(your_x_data)

Unsupervised

K-Means

from sklearn.cluster import KMeans
your_model = KMeans(n_clusters=4, init='random')
your_model.fit(x_training_data)

predictions = your_model.predict(your_x_data)

Validating the Model

accuracy, recall, precision, and F1 score

from sklearn.metrics import accuracy_score, recall_score, precision_score, f1_score
print(accuracy_score(true_labels, guesses))
print(recall_score(true_labels, guesses))
print(precision_score(true_labels, guesses))
print(f1_score(true_labels, guesses))

confusion matrix

from sklearn.metrics import confusion_matrix
print(confusion_matrix(true_labels, guesses))

Training sets and Test sets

from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.8, test_size=0.2)

Distances

Euclidean Distance

Manhattan Distance

Hamming Distance

1

2

click to edit

from scipy.spatial import distance

distance.euclidean()

.cityblock()

.hamming()

Correlation

click to edit