3 Types of Data in Machine Learning

Numerical
This represents some sort of quantitative measurement. Example: height of people, stock price, page load time etc. It can be further broken up into 2 parts:
Discrete data: This is integer based, often counts of some event. Example: “How many songs do a user like?” or “How many times a coin flipped to “head” ?”
Continuous data: It has an infinite number of possible values. Example: “How much time did it take for a user to buy?”
Categorical
This represents qualitative data with no apparent inherent mathematical meaning. Example: Yes or No, Sex, Race, Marital Status etc. These can take be assigned numbers like Yes(0) and No(1), but numbers have no mathematical meaning.
Ordinal
It has features of both numerical and categorical data. But the numbers placed in categories have mathematical meaning. Example: movies rating on 1–5, etc. These values have a mathematical meaning.
Therefore, we tend to overlook this step and jump straight into the water.

Comments

Feature Importance

Feature Importance for regression from sklearn . datasets import make _ regression # define dataset X , y = make_regression ( n_samples = 1000 , n_features = 10 , n_informative = 5 , random_state = 1 ) # summarize the dataset print ( X . shape , y . shape ) #linear regression feature importance from sklearn . datasets import make_regression from sklearn . linear_model import LinearRegression from matplotlib import pyplot # define dataset X , y = make_regression ( n_samples = 1000 , n_features = 10 , n_informative = 5 , random_state = 1 ) # define the model model = LinearRegression ( ) # fit the model model . fit ( X , y ) # get importance importance = model . coef _ # summarize feature importance for i , v in enumerate ( importance ) : print ( 'Feature: %0d, Score: %.5f' % ( i , v ) ) # plot feature importance pyplot . bar ( [ x for x in range ( len ( importance ) ) ] , importance ) pyplot . show ( ) feature importance for classification # test cl...

Process of Data Science

Feature Engineering

Feature Engineering is the way of extracting features from data and transforming them into formats that are suitable for Machine Learning algorithms. It is divided into 3 broad categories:- Feature Selection: All features aren't equal. It is all about selecting a small subset of features from a large pool of features . We select those attributes which best explain the relationship of an independent variable with the target variable. There are certain features which are more important than other features to the accuracy of the model. It is different from dimensionality reduction because the dimensionality reduction method does so by combining existing attributes, whereas the feature selection method includes or excludes those features. The methods of Feature Selection are Chi-squared test, correlation coefficient scores, LASSO, Ridge regression etc. Feature Transformation: It means transforming our original feature to the functions of or...

buddhareddydatascience

Search This Blog