Sunday, October 30, 2016

Udacity Machine Learning Nanodegree Cheatsheet Useful Functions and Libraries

# libraries
import numpy as np
import pandas as pd
# data processing
from sklearn.cross_validation  import ShuffleSplit
from sklearn.cross_validation import train_test_split

# scoring
from sklearn.metrics import r2_score

 # visualizations code
import visuals as vs

 # visual display for Jupyter notebooks
%matplotlib inline

 # Load dataset
data = pd.read_csv('xyz.csv')
target = data['col_xyz']
features = data.drop('col_xyz', axis = 1)

#data processing
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8, random_state=1)

 # Success
print "XYZ dataset has {} data points with {} variables each.".format(*data.shape)

 # Exploring dataset

# learning curve from sklearn.model_selection import learning_curve

from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import confusion_matrix
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import recall_score as recall
from sklearn.metrics import precision_score as precision

model selection

from sklearn.grid_search import GridSearchCV #legacy
from sklearn.model_selection import GridSearchCV #new release

No comments:

Post a Comment

Host an HTML website on Github in 5 minutes HD

Tutorial how to set up web hosting, personal portfolio website on Github in 5 minutes. More content coming to this paid channel including in...