> Preprocessing The Data > Evaluate Your Model’s Performance

Python For Data Science

Standardization Classification Metrics

Scikit-Learn Cheat Sheet >>>

>>>
>>>
from [Link] import StandardScaler

scaler = StandardScaler().fit(X_train)

standardized_X = [Link](X_train)

Accuracy Score
>>> [Link](X_test, y_test) #Estimator score method

>>> from [Link] import accuracy_score #Metric scoring functions

>>> standardized_X_test = [Link](X_test) >>> accuracy_score(y_test, y_pred)

Learn Scikit-Learn online at [Link]
Classification Report
Normalization >>> from [Link] import classification_report #Precision, recall, f1-score and support

>>> print(classification_report(y_test, y_pred))

>>> from [Link] import Normalizer

Confusion Matrix
>>> scaler = Normalizer().fit(X_train)

Scikit-learn >>>
>>>
normalized_X = [Link](X_train)

normalized_X_test = [Link](X_test)
>>> from [Link] import confusion_matrix

>>> print(confusion_matrix(y_test, y_pred))

Scikit-learn is an open source Python library that implements a range of Binarization Regression Metrics
machine learning, preprocessing, cross-validation and visualization

algorithms using a unified interface. >>> from [Link] import Binarizer

Mean Absolute Error
>>> binarizer = Binarizer(threshold=0.0).fit(X)
>>> from [Link] import mean_absolute_error

>>> binary_X = [Link](X)

A Basic Example >>> y_true = [3, -0.5, 2]

>>> mean_absolute_error(y_true, y_pred)

>>> from sklearn import neighbors, datasets, preprocessing

Encoding Categorical Features Mean Squared Error

>>> from sklearn.model_selection import train_test_split
>>> from [Link] import mean_squared_error

>>> from [Link] import accuracy_score

>>> from [Link] import LabelEncoder
>>> mean_squared_error(y_test, y_pred)
>>> iris = datasets.load_iris()
>>> enc = LabelEncoder()

>>> X, y = [Link][:, :2], [Link]

R² Score
>>> y = enc.fit_transform(y)
>>> X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=33)
>>> from [Link] import r2_score

>>> scaler = [Link]().fit(X_train)

>>> r2_score(y_true, y_pred)
>>>
>>>
X_train = [Link](X_train)

X_test = [Link](X_test)

Imputing Missing Values

>>> knn = [Link](n_neighbors=5)

>>> from [Link] import Imputer

Clustering Metrics
>>> [Link](X_train, y_train)

>>> y_pred = [Link](X_test)

>>> imp = Imputer(missing_values=0, strategy='mean', axis=0)

>>> imp.fit_transform(X_train) Adjusted Rand Index

>>> accuracy_score(y_test, y_pred)
>>> from [Link] import adjusted_rand_score

Generating Polynomial Features >>> adjusted_rand_score(y_true, y_pred)

> Loading The Data Also see NumPy & Pandas

>>> from [Link] import PolynomialFeatures

Homogeneity

>>> from [Link] import homogeneity_score

>>> poly = PolynomialFeatures(5)

>>> homogeneity_score(y_true, y_pred)
Your data needs to be numeric and stored as NumPy arrays or SciPy sparse matrices. Other types that are >>> poly.fit_transform(X)
convertible to numeric arrays, such as Pandas DataFrame, are also acceptable. V-measure
>>> import numpy as np
>>> from [Link] import v_measure_score

> Create Your Model

>>> X = [Link]((10,5))
>>> metrics.v_measure_score(y_true, y_pred)
>>> y = [Link](['M','M','F','F','M','F','M','M','F','F','F'])

>>> X[X < 0.7] = 0

Cross-Validation
Supervised Learning Estimators
> Training And Test Data Linear Regression
>>> from sklearn.cross_validation import cross_val_score

>>> print(cross_val_score(knn, X_train, y_train, cv=4))

>>> print(cross_val_score(lr, X, y, cv=2))

>>> from sklearn.linear_model import LinearRegression

>>> from sklearn.model_selection import train_test_split

>>> lr = LinearRegression(normalize=True)
>>> X_train, X_test, y_train, y_test = train_test_split(X,

y,

random_state=0)
Support Vector Machines (SVM)
>>> from [Link] import SVC

> Tune Your Model

>>> svc = SVC(kernel='linear')

Grid Search
> Model Fitting
Naive Bayes
>>> from sklearn.naive_bayes import GaussianNB

>>> gnb = GaussianNB() >>> from sklearn.grid_search import GridSearchCV

>>> params = {"n_neighbors": [Link](1,3),

Supervised learning KNN "metric": ["euclidean", "cityblock"]}

>>> [Link](X, y) #Fit the model to the data

>>> from sklearn import neighbors
>>> grid = GridSearchCV(estimator=knn,

>>> [Link](X_train, y_train)

>>> knn = [Link](n_neighbors=5) param_grid=params)

>>> [Link](X_train, y_train) >>> [Link](X_train, y_train)

>>> print(grid.best_score_)

Unsupervised Learning
Unsupervised Learning Estimators >>> print(grid.best_estimator_.n_neighbors)
>>> k_means.fit(X_train) #Fit the model to the data

>>> pca_model = pca.fit_transform(X_train) #Fit to data, then transform it

Principal Component Analysis (PCA) Randomized Parameter Optimization
>>> from [Link] import PCA

>>> pca = PCA(n_components=0.95) >>> from sklearn.grid_search import RandomizedSearchCV

> Prediction K Means

>>> params = {"n_neighbors": range(1,5), "weights": ["uniform", "distance"]}

>>> rsearch = RandomizedSearchCV(estimator=knn, param_distributions=params,

>>> from [Link] import KMeans

cv=4, n_iter=8, random_state=5)

Supervised Estimators >>> k_means = KMeans(n_clusters=3, random_state=0) >>> [Link](X_train, y_train)

>>> print(rsearch.best_score_)
>>> y_pred = [Link]([Link]((2,5))) #Predict labels

>>> y_pred = [Link](X_test) #Predict labels

>>> y_pred = knn.predict_proba(X_test) #Estimate probability of a label

Unsupervised Estimators
Learn Data Skills Online at [Link]
>>> y_pred = k_means.predict(X_test) #Predict labels in clustering algos