week 7(26-30 August)
DAY 1
Today
, we first started with our ISB video lecture no.3 which was about
"Bayesian Learning".In this lecture we learnt about different
distributions(Bernoulli, Categorical & continuous probability
densities).Next we learnt about Joint probability distributions and
marginalisation.It was explained using the concept of generative and
discriminative model.
After break Vikram sir give us overview about the "Feature Engineering".Feature engineering is the process of using domain knowledge of the data to create features that make machine learning algorithms work. If feature engineering is done correctly, it increases the predictive power of machine learning algorithms by creating features from raw data that help facilitate the machine learning process.After that sir discussed the problems that we were facing in EDA.
DAY2
Today Vikram sir gave us a hands on session on "RFE" i.e Recursive Feature Elimination.Recursive Feature Elimination or RFE uses a model ( eg. linear Regression or SVM) to select either the best or worst-performing feature, and then excludes this feature. The whole process is then iterated until all features in the dataset are used up ( or up to a user-defined limit). Sklearn conveniently possesses a RFE function via the sklearn.feature_selection call and we will use this along with a simple linear regression model for our ranking search as follows:
After we practised coding on the same and then continued with our ISB 3rd lecture and finished this with model for cascading with some probability based examples.
DAY 4
Today Vikram sir introduced us to a new topic "Featuretools".Featuretools is a python library for automated feature engineering. It uses Deep Feature Synthesis (DFS) to perform automated feature engineering.Featuretools can automatically create a single table of features for any "target entity".Sir explained this concept with the help of an example.we use a multi-table dataset of 3 million online grocery orders from Instacart to predict what a customer will buy next. We show how to generate features with automated feature engineering and build an accurate machine learning pipeline using Featuretools, which can be reused for multiple prediction problems.
Next , we started our next ISB video on "Clustering".The lecture started with the description of our first project i.e. News Recommender which is a cold start project which means we have to generate even the data for the first time users of this news recommender app.After that sir explained the basic approaches of clustering , one was partitioning method (k-means)and other was density based approach(db scan).
DAY 5
Yesterday Vikram sir told us to do some R&D on hypertools.So firstly we all were exploring about hypertools before the session and we found following points:
After half-time , we continued with clustering lecture.Today in this , we learnt some more approaches like hierarchial and model based approach and before that Gurmukh sir has already discussed the K-means clustering algorithm so it was easy to understand now.
After break Vikram sir give us overview about the "Feature Engineering".Feature engineering is the process of using domain knowledge of the data to create features that make machine learning algorithms work. If feature engineering is done correctly, it increases the predictive power of machine learning algorithms by creating features from raw data that help facilitate the machine learning process.After that sir discussed the problems that we were facing in EDA.
DAY2
Today in morning , first we had session with Virkam sir , he guided us further in feature engineering.He discussed feature selection
with us in which he said we have to train a model on the subset of
features and then store the result.Repeat this with different subsets
and compare them.This is known as sequential feature selection.He gave
some overview about Lasso Regression which is a part of Selection by
modelling.
Next
, we continued with the 3rd video of ISB , we learnt about probability
independence , prior and posterior probabilities , bayes rule with
example , bayesian belief network and then samples and estimation was
illustrated using examples of binary and continuous observation.
DAY 3
DAY 3
Today Vikram sir gave us a hands on session on "RFE" i.e Recursive Feature Elimination.Recursive Feature Elimination or RFE uses a model ( eg. linear Regression or SVM) to select either the best or worst-performing feature, and then excludes this feature. The whole process is then iterated until all features in the dataset are used up ( or up to a user-defined limit). Sklearn conveniently possesses a RFE function via the sklearn.feature_selection call and we will use this along with a simple linear regression model for our ranking search as follows:
# Construct our Linear Regression model lr = LinearRegression(normalize=True) lr.fit(X,Y) #stop the search when only the last feature is left rfe = RFE(lr, n_features_to_select=1, verbose =3 ) rfe.fit(X,Y) ranks["RFE"] = ranking(list(map(float, rfe.ranking_)), colnames, order=-1)
After we practised coding on the same and then continued with our ISB 3rd lecture and finished this with model for cascading with some probability based examples.
DAY 4
Today Vikram sir introduced us to a new topic "Featuretools".Featuretools is a python library for automated feature engineering. It uses Deep Feature Synthesis (DFS) to perform automated feature engineering.Featuretools can automatically create a single table of features for any "target entity".Sir explained this concept with the help of an example.we use a multi-table dataset of 3 million online grocery orders from Instacart to predict what a customer will buy next. We show how to generate features with automated feature engineering and build an accurate machine learning pipeline using Featuretools, which can be reused for multiple prediction problems.
Next , we started our next ISB video on "Clustering".The lecture started with the description of our first project i.e. News Recommender which is a cold start project which means we have to generate even the data for the first time users of this news recommender app.After that sir explained the basic approaches of clustering , one was partitioning method (k-means)and other was density based approach(db scan).
DAY 5
Yesterday Vikram sir told us to do some R&D on hypertools.So firstly we all were exploring about hypertools before the session and we found following points:
- Hypertools is a python library that reduces high dimensional data and plots it
- It uses PCA at it’s core and is built on top of libraries like seaborn, scikit-learn and matplotlib
- The visualizations it produces are intuitive and amazing
After half-time , we continued with clustering lecture.Today in this , we learnt some more approaches like hierarchial and model based approach and before that Gurmukh sir has already discussed the K-means clustering algorithm so it was easy to understand now.
Popular posts from this blog
Week 15 (8/10/18 - 12/10/18)
Statistics By Sehra SirWe had been having sessions with Sukhjit Sehra
Sir on statistics since the past week. This week we learned about the
following topics:
Probability and Probability DistributionsProbability theory developed from the study of games of chance like dice and cards. A process like flipping a coin, rolling a die or drawing a card from a deck is called probability experiments. An outcome is a specific result of a single trial of a probability experiment.
Probability Distributions
Probability theory is the foundation for statistical inference. A probability distribution is a device for indicating the values that a random variable may have. There are two categories of random variables. These are discrete random variables and continuous random variables.
Discrete random variable
The probability distribution of a discrete random variable specifies all possible values of a discrete random variable along with their respective probabilities.
Examples can be Frequency distribution…
Probability and Probability DistributionsProbability theory developed from the study of games of chance like dice and cards. A process like flipping a coin, rolling a die or drawing a card from a deck is called probability experiments. An outcome is a specific result of a single trial of a probability experiment.
Probability Distributions
Probability theory is the foundation for statistical inference. A probability distribution is a device for indicating the values that a random variable may have. There are two categories of random variables. These are discrete random variables and continuous random variables.
Discrete random variable
The probability distribution of a discrete random variable specifies all possible values of a discrete random variable along with their respective probabilities.
Examples can be Frequency distribution…
Week 22 (26/11/18 - 30/11/18)
Lecture - Design Thinking
This week we had a session with Mandeep Singh Kwatria on Design Thinking
to help thinking about good innovative ideas. Design Thinking is a
design methodology that provides a
solution-based approach to solving problems. It’s extremely useful in
tackling complex problems that are ill-defined or unknown, by
understanding the human needs involved, by re-framing the problem in
human-centric ways, by creating many ideas in brainstorming sessions,
and by adopting a hands-on approach in prototyping and testing.
The three Design Thinking Phases are:
InspireIdeateImplement A ground-breaking innovation will be desirable, feasible and viable.
Paddy Crop Project Along with other work, we also had a project from one of our professors related to paddy (confidential) which we worked on using the knowledge we got in this internship.
The three Design Thinking Phases are:
InspireIdeateImplement A ground-breaking innovation will be desirable, feasible and viable.
Paddy Crop Project Along with other work, we also had a project from one of our professors related to paddy (confidential) which we worked on using the knowledge we got in this internship.
Day 1 - Numpy Revision
Numpy Revision We made a python program for the following random walk question: Say
you are standing at the bottom of a staircase with a dice. With each
throw of the dice, you either move down one step (if you get a 1 or 2 on
the dice) or move up one step (if you get a 3, 4 or 5 on the dice). If
you throw a 6 on the dice, you throw the dice again and move up the
staircase by the number you get on that second throw. Note if you are on
the base of the staircase you cannot move down! What is the probability
that you will reach more than 60 steps after 250 throws of the dice?
This question required the knowledge of np.random.seed. It seeds the generator. It makes the random numbers predictable. When the value is reset, the same numbers will appear every time. If a seed is not assigned, NumPy automatically selects a random seed value based on the system's random number generator device or on the clock
The code was as follows:
import numpy as np
np.random.seed(123)
allwalks = []
for i in range…
This question required the knowledge of np.random.seed. It seeds the generator. It makes the random numbers predictable. When the value is reset, the same numbers will appear every time. If a seed is not assigned, NumPy automatically selects a random seed value based on the system's random number generator device or on the clock
The code was as follows:
import numpy as np
np.random.seed(123)
allwalks = []
for i in range…
Comments