Ad

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 visuals.py
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
my_dataframe.head()
my_dataframe.head(5)
my_dataframe.describe()


# 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

Useful sklearn modules

from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.cross_validation import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn import metrics
from sklearn.metrics import roc_curve, auc
from nltk.stem.porter import PorterStemmer

Subscribe to our mailing list


No comments:

Post a Comment

Applying for jobs at the Lending Club

We tried to figure out Lending Club 's tech stack for 2019. Our analysis shows Lending Club asks for skills in Python, Tableau, SQL and ...