notions

Question 1

actionable insight

Answer 1

an operational insight that can be implemented

Question 2

bad data

Answer 2

garbage in - garbage out

Question 3

re-create analysis

Answer 3

is quite difficult but important

Question 4

bias

Answer 4

things that can influence the decision in the wrong wayy

Question 5

analytics workflow

Answer 5

modularity - which tools approaches are used

Question 6

Directed acyclic graph

Answer 6

s a directed graph with no directed cycles. That is, it consists of vertices and edges, with each edge directed from one vertex to another, such that following those directions will never form a closed loop.

Question 7

airflow

Answer 7

workflow manager to not user crontab

Question 8

Sum of squares total / regression / error

Answer 8

SST/TSS - sum of squares of for E 1->n (y1 - mean)^2
SSR/ESS - SS Regression/ explained sum of squares - of difference between the mean value and predicted value
ESS - sum of differences between predict value and real on

Question 9

Sum of squares total / regression / error

Answer 9

SST/TSS - sum of squares of for E 1->n (y1 - mean)^2
SSR/ESS - SS Regression/ explained sum of squares - of difference between the mean value and predicted value
ESS/RSS(Residual sum of square) - sum of differences between predict value and real on

Question 10

Sum of squares total / regression / error

Answer 10

SST/TSS - sum of squares of for E 1->n (y1 - mean)^2
SSR/ESS - SS Regression/ explained sum of squares - of difference between the mean value and predicted value
ESS/RSS(Residual sum of square) - sum of differences between predict value and real one

SST = SSR + ESS

Question 11

Sum of squares total / regression / error

Answer 11

SST/TSS - sum of squares of for E 1->n (y1 - mean)^2
SSR/ESS - SS Regression/ explained sum of squares - of difference between the mean value and predicted value
SSE/RSS(Residual sum of square) - sum of differences between predict value and real on

SST = SSR + ESS

Question 12

Depndent variable

Answer 12

The one we are trying to predict

Question 13

OLS

Answer 13

Ordinary Least Squares

Question 14

OLS

Answer 14

Ordinary Least Squares (min SSE)

Question 15

R-squared

Answer 15

R^2 = SSR/SST, 1 is best, 0 is worst

Question 16

R-squared

Answer 16

R^2 = SSR/SST, 1 is best, 0 is worst

R-squared measures how much of the total variability is explained by this model

Question 17

adjusted R-squared

Answer 17

measures how well your model fits the data. However, it penalizes the use of variables that are meaningless for the regression.

Question 18

F-statistic

Answer 18

??

Question 19

Linearity

Answer 19

Is the function linear? Does it fit well?

Question 20

No endegeneity

Answer 20

???

Question 21

Feature/target in ML

Answer 21

independent variable(feature), used to predict dependent variable(target)

Question 22

Regression intercept

Answer 22

A point where regression line crosses y-axis

Question 23

Regression coefficient

Answer 23

the coefficient on which should we multiple the feature

Question 24

p-value of the feature

Answer 24

The p-value for each term tests the null hypothesis that the coefficient is equal to zero (no effect). A low p-value (< 0.05) indicates that you can reject the null hypothesis (means that feature can be used)

Question 25

F-regression

Answer 25

Creates regressions for a feature(in case we have many of them) and a target

Question 26

mean vs average

Answer 26

mean is the value in 50%, average is sum divided by number of elements

Question 27

standardization

Answer 27

Find the mean and std deviation. value-mean/deviation

Question 28

underfitting/overfitting

Answer 28

underfitting - low accuracy(doesn't capture any logic)/ overfitting too much accuracy (capture all the noise). Can be resolved by train(75%) and test(25%) datasets.

Question 29

Multicollinearity

Answer 29

???

Question 30

Dummy variables

Answer 30

In case of categories(BMW, AUDI, Opel) we want to create n-1 columns with dummy variables (1 if BMW, 0 if not) In this case no new column for Opel as it is obvious that if it's not BMW or Audi it is opel

Question 31

Data cleaning

Answer 31

Remove outliers, qunatile, remove missing values

Question 32

Models: linear, quadratic, exponential, logistic

Answer 32

Logistic: categorical regression

Question 33

MLE

Answer 33

maximum likelihood estimation

Question 34

Clusters

Answer 34

Maximize the similarity in cluster and dissimilarity between clusters

Question 35

Cluster analysis

Answer 35

unsupervised learning as we don't know the result. Classification though deals with known outcomes and can be trained on train data.

Question 36

Centroid

Answer 36

Center of mass of all data points in cluster analysis

Question 37

K-means

Answer 37

1) Choose K. 2) Specify seed(centroid) 3) Assign each point to the closest centroid 4) Adjust the centroid based on selected points

Question 38

Cluster analysis

Answer 38

unsupervised learning as we don't know the result. Classification although deals with known outcomes and can be trained on train data.

Question 39

Centroid

Answer 39

Center of the mass of all data points in cluster analysis

Question 40

K-means

Answer 40

1) Choose K. 2) Specify seed(centroid) 3) Assign each point to the closest centroid 4) Adjust the centroid based on selected points Repeat 3

Question 41

WCSS

Answer 41

``` determine the number of clusters Within Cluster Sum of Squares Elbow method To get WCSS kmeans.inertia_ ```

Question 42

Cluster seeds

Answer 42

We need to choose points from which to build our clusters. There's k-means++ method for this It is already integrated to KMeans

Question 43

Cluster analysis pros and cons

Answer 43

``` Pros: Simple to understand Fast to cluster Widely available Easy to implement ``` ``` Cons: We need to pick K (Elbow method) Sensitive to initialization (k-means++) Sensitive to outliers (remove outliers) Produces spherical solutions (as we use euclidian distance from centroid) Standardization ```

Question 44

Class of clusters

Answer 44

Flat (Kmeans) Hierarchical (Species)

Question 45

IQR

Answer 45

Intra Quartal Range