SLIDE 1
Regression models
P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON
Conor Dewey
Data Scientist, Squarespace
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Getting started
Wikimedia
1
Regression models P R AC TIC IN G STATISTIC S IN TE R VIE W QU E - - PowerPoint PPT Presentation
Regression models P R AC TIC IN G STATISTIC S IN TE R VIE W QU E - - PowerPoint PPT Presentation
Regression models P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON Conor De w e y Data Scientist , Sq u arespace Getting started 1 Wikimedia PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON Ass u mptions Linear
SLIDE 2
SLIDE 3
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Assumptions
Linear relationship Errors are normally distributed Homoscedasticity Independent observations
SLIDE 4
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Linear regression
Wikipedia
1
SLIDE 5
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Linear regression
SLIDE 6
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Example: linear regression
from sklearn.linear_model import LinearRegression lm = LinearRegression() lm.fit(X_train, y_train) LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)
SLIDE 7
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Example: linear regression
coef = lm.coef_ print(coef) [0.79086669]
SLIDE 8
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Logistic regression
Wikimedia
1
SLIDE 9
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Logistic regression
SLIDE 10
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Example: logistic regression
from sklearn.linear_model import LogisticRegression clf = LogisticRegression(solver='lbfgs') clf.fit(X_train, y_train) LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True, intercept_scaling=1, max_iter=100, multi_class='warn', n_jobs=None, penalty='l2', random_state=None, solver='lbfgs', tol=0.0001, verbose=0, warm_start=False)
SLIDE 11
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Example: logistic regression
coefs = clf.coef_ print(coefs) [[0.4015177 3.85056451]] accuracy = clf.score(X_test, y_test) print(accuracy) 0.8583333333333333
SLIDE 12
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Summary
Review Assumptions Linear regression Logistic regression
SLIDE 13
Let's prepare for the interview!
P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON
SLIDE 14
Evaluating models
P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON
Conor Dewey
Data Scientist, Squarespace
SLIDE 15
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Regression techniques
R-squared Mean absolute error (MAE) Mean squared error (MSE)
SLIDE 16
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
R-squared
Wikimedia
1
SLIDE 17
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
MAE vs. MSE
Wikimedia
1
SLIDE 18
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
MAE vs. MSE
120 Data Science Interview Questions
1
SLIDE 19
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Classification techniques
Precision Recall Confusion matrices
SLIDE 20
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Precision
SLIDE 21
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Recall
SLIDE 22
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Confusion matrix
AB Tasty
1
SLIDE 23
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Confusion matrix
AB Tasty
1
SLIDE 24
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Confusion matrix
AB Tasty
1
SLIDE 25
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Summary
R-squared Mean absolute error (MAE) vs. mean squared error (MSE) Precision and recall
SLIDE 26
Let's prepare for the interview!
P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON
SLIDE 27
Missing data and
- utliers
P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON
Conor Dewey
Data Scientist, Squarespace
SLIDE 28
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Handling missing data
Drop the whole row Impute missing values
SLIDE 29
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Drop the whole row
df.dropna(inplace=True)
SLIDE 30
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Impute missing values
Constant value Randomly selected record Mean, median, or mode Value estimated by another model
SLIDE 31
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
A few useful functions
isnull() dropna() fillna()
SLIDE 32
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Dealing with outliers
Standard deviations Interquartile range (IQR)
SLIDE 33
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Standard deviations
Wikimedia
1
SLIDE 34
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Interquartile range (IQR)
Wikimedia
1
SLIDE 35
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Summary
Drop the whole row Impute missing values Standard deviations Interquartile range
SLIDE 36
Let's prepare for the interview!
P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON
SLIDE 37
Bias-variance tradeoff
P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON
Conor Dewey
Data Scientist, Squarespace
SLIDE 38
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Types of error
Bias error Variance error Irreducible error
SLIDE 39
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Bias error
How to Use Machine Learning to Predict the Quality of Wines
1
SLIDE 40
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Variance error
How to Use Machine Learning to Predict the Quality of Wines
1
SLIDE 41
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Bias-variance tradeoff
Sco Fortmann
1
SLIDE 42
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Summary
Types of error Bias error Variance error Bias-variance tradeo
SLIDE 43
Let's prepare for the interview!
P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON
SLIDE 44
Wrapping up
P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON
Conor Dewey
Data Scientist, Squarespace
SLIDE 45
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Chapter 1: Probability and sampling distributions
Conditional probabilities Central limit theorem Probability distributions
SLIDE 46
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Chapter 2: Exploratory data analysis
Descriptive statistics Categorical data Encoding techniques Multivariate relationships
SLIDE 47
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Chapter 3: Statistical experiments and significance testing
Condence intervals Hypothesis testing Power analysis Multiple comparisons
SLIDE 48
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Chapter 4: Regression and classification
Linear regression Logistic regression Missing data and outliers Bias-variance tradeo
SLIDE 49
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Some advice
Simulate the interview environment Practice explaining big concepts Know the business or product well Come prepared with ideas
SLIDE 50
PRACTICING STATISTICS INTERVIEW QUESTIONS IN PYTHON
Resources
Data Science Career Resources Repo Practical Statistics for Data Scientists 120 Data Science Interview Questions Advice Applying to Data Science Jobs
SLIDE 51
Good luck and thank you!
P R AC TIC IN G STATISTIC S IN TE R VIE W QU E STION S IN P YTH ON