Google Advanced Data Analytics Flashcards
(471 cards)
1
Q
A way to compare two versions of something to find out which version performs better
A
A/B testing
2
Q
(Refer to observed values)
A
Absolute values
3
Q
Refers to the proportion of data points that were correctly categorized
A
Accuracy
4
Q
A Tableau tool to help an audience interact with a visualization or dashboard by allowing control of selection
A
Action
5
Q
Refers to allowing team members, bosses, and other collaborative stakeholders to share their own points of view before offering responses
A
Active listening
6
Q
(Refer to adaptive boosting)
A
AdaBoost
7
Q
A boosting methodology where each consecutive base learner assigns greater weight to the observations incorrectly predicted by the preceding learner
A
Adaptive boosting
8
Q
The concept that if the events A and B are mutually exclusive, then the probability of A or B happening is the sum of the probabilities of A and B
A
Addition rule (for mutually exclusive events):
9
Q
A variation of R² that accounts for having multiple independent variables present in a linear regression model
A
Adjusted R²
10
Q
The metric used to calculate the distance between points/clusters
A
Affinity
11
Q
A pandas groupby method that allows the user to apply multiple calculations to groups of data
A
agg():
12
Q
A clustering methodology that works by first assigning every point to its own cluster, then progressively combining clusters based on intercluster distance
A
Agglomerative clustering
13
Q
Data from a significant number of users that has eliminated personal information
A
Aggregate information
14
Q
A set of instructions for solving a problem or accomplishing a task
A
Algorithm
15
Q
A process that allows the user to assign an alternate name—or alias—to something
A
Aliasing
16
Q
A group of statistical techniques that test the difference of means between three or more groups
A
Analysis of Variance (ANOVA)
17
Q
A data professional who supervises analytical strategy for an organization, often managing multiple groups
A
Analytics Team Manager
18
Q
Stage of the PACE workflow where the necessary data is acquired from primary and secondary sources and then cleaned, reorganized, and analyzed
A
Analyze stage
19
Q
A statistical technique that tests the difference of means between three or more groups while controlling for the effects of covariates, or variable(s) irrelevant to the test
A
ANCOVA (Analysis of Covariance)
20
Q
A method that adds an element to the end of a list
A
append():
21
Q
An ordered collection of items of a single data type
A
Array:
22
Q
A function for converting input to an array
A
Array():
23
Q
Information given to a function in its parentheses
A
Argument
24
Q
Refers to computer systems able to perform tasks that normally require human intelligence
A
Artificial intelligence (AI)
25
The process of storing a value in a variable
Assignment
26
A value associated with an object or class which is referenced by name using dot notation
Attribute
27
Average: The distance between each cluster’s centroid and other clusters’ centroids
Average
28
A stepwise variable selection process that begins with the full model, with all possible independent variables, and removes the independent variable that adds the least explanatory power to the model
Backward elimination
29
A technique used by certain kinds of models that use ensembles of base learners to make predictions; refers to the combination of bootstrapping and aggregating
Bagging
30
Each individual model that comprises an ensemble
Base learner
31
(Refer to Bayes’ theorem)
Bayes’ rule
32
An equation that can be used to calculate the probability of an outcome or class, given the values of predictor variables
Bayes’ theorem
33
(Refer to Bayesian statistics)
Bayesian inference
34
A powerful method for analyzing and interpreting data in modern data analytics; also referred to as Bayesian inference
Bayesian statistics
35
The line that fits the data best by minimizing some loss function or error
Best fit line
36
In data structuring, refers to organizing data results in groupings, categories, or variables that are misrepresentative of the whole dataset
Bias
37
Balance between two model qualities, bias and variance, to minimize overall error for unobserved data
Bias-variance trade-off
38
A segment of data that groups values into categories
Bin
39
Grouping continuous values into a smaller number of categories, or intervals
Binning
40
A discrete distribution that models the probability of events with only two possible outcomes: success or failure
Binomial distribution
41
A technique that models the probability of an observation falling into one of two categories, based on one or more independent variables
Binomial logistic regression
42
An assumption stating that there should be a linear relationship between each X variable and the logit of the probability that Y equals one
Binomial logistic regression linearity assumption
43
Any model whose predictions cannot be precisely explained
Black-box model
44
A data type that has only two possible values, usually true or false
Boolean
45
A data type that has only two possible values, usually true or false
Boolean data
46
A filtering technique that overlays a Boolean grid onto a dataframe in order to select only the values in the dataframe that align with the True values of the grid
Boolean masking
47
A technique that that builds an ensemble of weak learners sequentially, with each consecutive learner trying to correct the errors of the one that preceded it
Boosting
48
Refers to sampling with replacement
Bootstrapping
49
A data visualization that depicts the locality, spread, and skew of groups of values within quartiles
Box plot
50
The ability of a program to alter its execution sequence
Branching
51
A keyword that lets a user escape a loop without triggering any ELSE statement that follows it in the loop
break
52
(Refer to Business Intelligence Engineer)
Business Intelligence Analyst:
53
A data professional who uses their knowledge of business trends and databases to organize information and make it accessible; also referred to as a Business Intelligence Analyst
Business Intelligence Engineer
54
Data that is divided into a limited number of qualitative groups
Categorical data:
55
Variables that contain a finite number of groups or categories
Categorical variables:
56
Describes a cause-and-effect relationship where one variable directly causes the other to change in a particular way
Causation:
57
The modular code input and output fields into which Jupyter Notebooks are partitioned
Cells:
58
The idea that the sampling distribution of the mean approaches a normal distribution as the sample size increases
Central Limit Theorem:
59
The center of a cluster determined by the mathematical mean of all the points in that cluster
Centroid:
60
A hypothesis test that determines whether an observed categorical variable follows an expected distribution
Chi-squared (χ²) Goodness of Fit Test:
61
A hypothesis test that determines whether or not two categorical variables are associated with each other
Chi-squared (χ²) Test for Independence:
62
An executive-level data professional who is responsible for the consistency, accuracy, relevancy, interpretability, and reliability of the data a team provides
Chief Data Officer:
63
A node that is pointed to from another node
Child node:
64
When a dataset has a predictor variable that contains more instances of one outcome than another
Class imbalance:
65
An object’s data type that bundles data and functionality together
Class:
66
A type of probability based on formal reasoning about events with equally likely outcomes
Classical probability:
67
The process of removing errors that might distort your data or make it less useful; one of the six practices of EDA
Cleaning:
68
A probability sampling method that divides a population into clusters, randomly selects certain clusters, and includes all members from the chosen clusters in the sample
Cluster random sample:
69
A technique used by recommendation systems to make comparisons based on who else liked the content
Collaborative filtering:
70
A group of abnormal points, following similar patterns and isolated from the rest of the population
Collective outliers:
71
An operator that compares two values and produces Boolean values (True/False)
Comparator:
72
In statistics, refers to an event not occuring
Complement of an event:
73
The maximum pairwise distance between clusters
Complete:
74
A concept stating that the probability that event A does not occur is one minus the probability of A
Complement rule:
75
Refers to defining attributes and methods at the instance level to have a more differentiated relationship between objects in the same class
Composition:
76
The process of giving instructions to a computer to perform an action or set of actions
Computer programming:
77
A pandas function that combines data either by adding it horizontally as new columns for existing rows or vertically as new rows for existing columns
concat():
78
To link or join together
Concatenate:
79
Refers to building longer strings out of smaller strings
Concatenation:
80
Refers to the probability of an event occurring given that another event has already occurred
Conditional probability:
80
A section of code that directs the execution of programs
Conditional statement:
81
The area surrounding a line that describes the uncertainty around the predicted outcome at every value of X
Confidence band:
82
A range of values that describes the uncertainty surrounding an estimate
Confidence interval:
83
A measure that expresses the uncertainty of the estimation process
Confidence level:
84
A graphical representation of how accurate a classifier is at predicting the labels for a categorical variable
Confusion matrix:
85
Stage of the PACE workflow where data models and machine learning
algorithms are built, interpreted, and revised to uncover relationships within the data and help unlock insights from those relationships
Construct stage:
86
A special method to add values to an instance in object creation
Constructor:
87
A technique used by recommendation systems to make comparisons based on attributes of content
Content-based filtering:
88
Normal data points under certain conditions but become anomalies under most other conditions
Contextual outliers:
89
A variable that takes all the possible values in some range of numbers
Continuous random variable:
90
A mathematical concept indicating that a measure or dimension has an infinite and uncountable number of outcomes
Continuous:
91
Variables that can take on an infinite and uncountable set of values
Continuous variables:
92
A non-probability sampling method that involves choosing members of a population that are easy to contact or reach
Convenience sample:
93
Measures the way two variables tend to change together
Correlation:
94
A process that uses different portions of the data to test and train a model on different iterations
Cross-validation:
95
A plaintext file that uses commas to separate distinct values from one another; Stands for "comma-separated values”
CSV file:
96
The business term that describes how many and at what rate customers stop using a product or service, or stop doing business with a company
Customer churn:
97
The process of formatting data and removing unwanted material
Data cleaning:
97
The process of protecting people's private or sensitive data by eliminating PII
Data anonymization:
98
A data professional who makes data accessible, ensures data ecosystems offer reliable results, and manages infrastructure for data across enterprises
Data engineer:
99
Well-founded standards of right and wrong that dictate how data is collected, shared, and used
Data ethics:
100
A process for ensuring the formal management of a company’s data assets
Data governance:
101
Any individual who works with data and/or has data skills
Data professional:
102
The discipline of making data useful
Data science:
103
A data professional who works closely with analytics to provide meaningful insights that help improve current business operations
Data scientist:
104
The location where data originates
Data source:
105
The practices of an organization that ensures that data is accessible, usable, and safe
Data stewardship:
106
An attribute that describes a piece of data based on its values, its programming language, or the operations it can perform
Data type:
107
A collection of data values or objects that contain different data types
Data structure:
108
A two-dimensional, labeled data structure with rows and columns
DataFrame:
109
A graph, chart, diagram, or dashboard that is created as a representation of information
Data visualization:
110
A file type used to store data, often in tables, indexes, or fields
Database (DB) file:
111
A two-dimensional data-structure organized into rows and columns
Dataframe:
112
A clustering methodology that searches data space for continuous regions of high density; stands for “density-based spatial clustering of applications with noise”
DBSCAN:
113
Troubleshooting, or searching for errors in a script or program
Debugging:
114
A node of the tree where decisions are made
Decision node:
115
A flowchart-like structure that uses branching paths to predict the outcomes of events, or the probability of certain outcomes
Decision tree:
116
The elimination or removal of matching data values in a dataset
Deduplication:
117
A keyword that defines a function at the start of the function block
def:
118
The concept that two events are dependent if one event changes the probability of the other event
Dependent events:
119
The variable a given model estimates
Dependent variable (Y):
120
A type of statistics that summarizes the main features of a dataset
Descriptive statistics:
121
A function that returns the statistical summary of a dataframe or series, including mean, standard deviation, and minimum and maximum column values.
Describe():
122
A function used to create a dictionary
dict():
123
A data structure that consists of a collection of key-value pairs
Dictionary:
124
A function that finds the elements present in one set but not the other
difference():
125
Qualitative data values used to categorize and group data to reveal details about it
Dimensions:
126
The process data professionals use to familiarize themselves with the data so they can start conceptualizing how to use it; one of the six practices of EDA
Discovering:
127
Features with a countable number of values between any two values
Discrete features:
128
A variable that has a countable number of possible values
Discrete random variable:
129
A mathematical concept indicating that a measure or dimension has a finite and countable number of outcomes
Discrete:
130
A hyperparameter in agglomerative clustering models that determines the distance above which clusters will not be merged
distance_threshold:
131
An in-depth guide that is written by the developers who created a package that features very specific information on various functions and features
Documentation:
132
How to access the methods and attributes that belong to an instance of a class
Dot notation:
133
A group of text that explains what a method or function does; also referred to as a “docstring”
Documentation string:
134
The process of removing some observations from the majority class, making it so they make up a smaller percentage of the dataset than before
Downsampling:
135
Variables with values of 0 or 1 that indicate the presence or absence of something
Dummy variables:
136
A NumPy attribute used to check the data type of the contents of an array
dtype:
137
Variables that can point to objects of any data type
Dynamic typing:
138
A value the user inputs or the output of a program, an operation, or a function
Dynamic value:
139
A branch of economics that uses statistics to analyze economic problems
Econometrics:
140
A way of distributing computational tasks over a bunch of nearby processors (i.e., computers) that is good for speed and resiliency and does not depend on a single source of computational power
Edge computing:
141
A reserved keyword that executes subsequent conditions when the previous conditions are not true
elif:
142
A reserved keyword that executes when preceding conditions evaluate as False
else:
143
A type of probability based on experimental or historical data
Empirical probability:
144
A concept stating that the values on a normal curve are distributed in a regular pattern, based on their distance from the mean
Empirical rule:
145
Refers to building multiple models and aggregating their predictions
Ensemble learning:
146
In DBSCAN clustering models, a hyperparameter that determines the radius of a search area from any given point
eps (Epsilon):
147
(Refer to ensemble learning)
Ensembling:
148
A built-in function that iterates through a sequence and tracks each element and its place in the index
Enumerate():
149
In a regression model, the natural noise assumed to be in a model
Errors:
150
A character that changes the typical behavior of the characters that follow it
Escape character:
151
Stage of the PACE workflow where a data professional will present findings with internal and external stakeholders, answer questions, consider different viewpoints, and make recommendations
Execute stage:
152
(Refer to independent variable)
Explanatory variable:
153
The process of converting a data type of an object to a required data type
Explicit conversion:
154
The process of investigating, organizing, and analyzing datasets and summarizing their main characteristics, often by employing data wrangling and visualization methods; the six main practices of EDA are: discovering, structuring, cleaning, joining, validating, and presenting
Exploratory data analysis (EDA):
155
Expression: A combination of numbers, symbols, or other variables that produce a result when evaluated
Expression:
156
Quantifies the difference between the amount of variance that is left unexplained by a reduced model that is explained by the full model
Extra Sum of Squares F-test:
157
The process of retrieving data out of data sources for further data processing
Extracting:
158
A model’s ability to predict new values that fall outside of the range of values in the training data
Extrapolation:
159
The harmonic mean of precision and recall
F1-Score:
160
A test result that indicates something is present when it really is not
False positive:
161
The process of using practical, statistical, and data science knowledge to select, transform, or extract characteristics, properties, and attributes from raw data
Feature engineering:
162
A type of feature engineering that involves taking multiple features to create a new one that would improve the accuracy of the algorithm
Feature extraction:
163
A type of feature engineering that involves selecting the features in the data that contribute the most to predicting the response variable
Feature selection:
164
A type of feature engineering that involves modifying existing features in a way that improves accuracy when training the model
Feature transformation:
165
The process of selecting a smaller part of a dataset based on specified values and using it for viewing or analysis
Filtering:
166
Data that was gathered from inside your own organization
First-party data:
167
A data type that represents numbers that contain decimals
Float:
168
A piece of code that iterates over a sequence of values
For loop:
169
A string method that formats and inserts specific substrings into designated places within a larger string
format():
170
A stepwise variable selection process that begins with the null mode—with zero independent variables—and considers all possible variables to add; incorporates the independent variable that contributes the most explanatory power to the model
Forward selection:
171
A body of reusable code for performing specific processes or tasks
Function:
172
A function that returns an object (iterator) which can be iterated over (one value at a time)
Generator():
173
Values that are completely different from the overall data group and have no association with any other outliers
Global outliers:
174
A variable that can be accessed from anywhere in a program or script
Global variable:
175
Model ensembles that use gradient boosting
Gradient boosting machines (GBMs):
176
A boosting methodology where each base learner in the sequence is built to predict the residual errors of the model that preceded it
Gradient boosting:
177
A tool to confirm that a model achieves its intended purpose by systematically checking every combination of hyperparameters to identify which set produces the best results, based on the selected metric
GridSearch:
178
A pandas DataFrame method that groups rows of the dataframe together based on their values at one or more columns, which allows further analysis of the groups
groupby():
179
Grouping: The process of aggregating individual observations of a variable into groups
Grouping:
180
An event where programmers and data professionals come together and work on a project
Hackathon:
181
A function that returns a preview of the column names and the first few rows of a dataset
Head():
182
A type of data visualization that depicts the magnitude of an instance or set of values based on two colors
Heatmap:
183
A Python help function used to display the documentation of modules, functions, classes, keywords, and more
Help():
184
A data visualization that depicts an approximate representation of the distribution of values in a dataset
Histogram:
185
A random sample of observed data that is not used to fit the model
Hold-out sample:
186
An assumption of simple linear regression stating that the variation of the residuals (errors) is constant or similar across the model
Homoscedasticity assumption:
187
Hyperparameters: Parameters that can be set by the modeler before the model is trained
Hyperparameters:
188
Refers to changing parameters that directly affect how the model trains, before the learning process begins
Hyperparameter tuning:
189
A theory or an explanation, based on evidence, that is not yet proven true
Hypothesis:
190
A statistical procedure that uses sample data to evaluate an assumption about a population parameter
Hypothesis testing:
191
A reserved keyword that sets up a condition in Python
if:
192
A type of notation in pandas that indicates when the user wants to select by integer-location-based position
iloc[]:
193
The concept that a data structure or element’s values can never be altered or updated
Immutability:
194
A data type in which the values can never be altered or updated
Immutable data type:
195
The process Python uses to automatically convert one data type to another without user involvement
Implicit conversion:
196
A statement that uses the import keyword to load an external library, package, module, or function into the computing environment
Import statement:
197
The concept that two events are independent if the occurrence of one event does not change the probability of the other event
Independent events:
198
An assumption of simple linear regression stating that each observation in the dataset is independent
Independent observation assumption:
199
The variable whose trends are associated with the dependent variable
Independent variable (X):
200
A string method that outputs the index number of a character in a string
index():
201
A way to refer to the individual items within an iterable by their relative position
Indexing:
202
The sum of the squared distances between each observation and its nearest centroid
Inertia:
203
Inferential statistics: A type of statistics that uses sample data to draw conclusions about a larger population
Inferential statistics:
204
Gives the total number of entries, along with the data types—called Dtypes in pandas—of the individual entries
Info():
205
Refers to letting a programmer build relationships between concepts and group them together to reduce code duplication
Inheritance:
206
A way of combining data such that only the keys that are in both dataframes get included in the merge
Inner join:
207
Input validation: The practice of thoroughly analyzing and double-checking to make sure data is complete, error-free, and high-quality
Input validation:
208
Information entered into a program
Input:
209
A Python function that can be used to ask a question in a message and store the answer in a variable
Input():
210
A function that takes an index as the first parameter and an element as the second parameter, then inserts the element into a list at the given index
insert():
211
A variable that is declared in a class outside of other methods or blocks
Instance variable:
212
Refers to creating a copy of the class that inherits all class variables and methods
Instantiation:
213
A standard integer data type, representing numbers somewhere between negative nine quintillion and positive nine quintillion
Int64:
214
A data type used to represent whole numbers without fractions
Integer:
215
A piece of software that has an interface to write, run, and test a piece of code
Integrated Development Environment (IDE):
216
Represents how the relationship between two independent variables is associated with changes in the mean of the dependent variable
Interaction term:
217
The y value of the point on the regression line where it intersects with the y-axis
Intercept (constant 𝐵0):
218
Traits that focus on communicating and building relationships
Interpersonal skills:
219
The distance between the first quartile (Q1) and the third quartile (Q3)
Interquartile range:
220
intersection(): A function that finds the elements that two sets have in common
intersection():
221
A sample statistic plus or minus the margin of error
Interval:
222
A calculation that uses a range of values to estimate a population parameter
Interval estimate:
223
A rule that checks objects and classes for ancestry
Is:
224
A dictionary method to retrieve both the dictionary’s keys and values
items():
225
An object that’s looped, or iterated, over
Iterable:
226
The repeated execution of a set of statements, where one iteration is the single execution of a block of code
Iteration:
227
The process of augmenting data by adding values from other datasets; one of the six practices of EDA
Joining:
228
A data storage file that is saved in a JavaScript format
JSON file:
229
An open-source web application for creating and sharing documents containing live code, mathematical formulas, visualizations, and text
Jupyter Notebook:
230
An unsupervised partitioning algorithm used to organize unlabeled data into groups, or clusters
K-means:
231
An underlying core program, like Python
Kernel:
232
The shared points of reference between different dataframes
Keys:
233
A dictionary method to retrieve only the dictionary’s keys
keys():
234
A special word in a programming language that is reserved for a specific purpose and that can only be used for that purpose
Keyword:
235
Data transformation technique where each category is assigned a unique number instead of a qualitative value
Label encoding:
236
The nodes where a final prediction is made
Leaf node:
237
In XGBoost, a hyperparameter that specifies how much weight is given to each consecutive tree’s prediction in the final ensemble
learning_rate:
238
A way of combining data such that all of the keys in the left dataframe are included, even if they aren’t in the right dataframe
Left join:
239
A function used to measure the length of strings
Len():
240
A reusable collection of code; also referred to as a “package”
Library:
241
The probability of observing the actual data, given some set of beta parameters
Likelihood:
242
A collection of an infinite number of points extending in two opposite directions
Line:
243
A technique that estimates the linear relationship between a continuous dependent variable and one or more independent variables
Linear regression:
244
An assumption of simple linear regression stating that each predictor variable (Xi) is linearly related to the outcome variable (Y)
Linearity assumption:
245
A nonlinear function that connects or links the dependent variable to the independent variables mathematically
Link function:
246
The method used to determine which points/clusters to merge
Linkage:
247
A data structure that helps store and manipulate an ordered collection of items
List:
248
Formulaic creation of a new list based on the values in an existing list
List comprehension:
249
The percentage of the population in a given age group that can read and write
Literacy rate:
250
Notation that is used to select pandas rows and columns by name
loc[]:
251
(Refer to logit)
Log-Odds function:
252
An operator that connects multiple statements together and performs complex comparisons
Logical operator:
253
A technique that models a categorical dependent variable (Y) based on one or more independent variables (X)
Logistic regression:
254
The logarithm of the odds of a given probability
Logit:
255
A block of code used to carry out iterations
Loop:
256
A function that measures the distance between the observed values and the model’s estimated values
Loss function:
257
When constructing an interval, the calculation of the sample means minus the margin of error
Lower limit:
258
The use and development of algorithms and statistical models to teach computer systems to analyze and discover patterns in data
Machine learning:
259
The average of the absolute difference between the predicted and actual values
MAE (Mean Absolute Error):
260
Commands that are built into IPython to simplify common tasks
Magic commands:
261
(Refer to magic commands)
Magics:
262
An extension of ANCOVA and MANOVA that compares how two or more continuous outcome variables vary according to categorical independent variables, while controlling for covariates
MANCOVA (Multivariate Analysis of Covariance):
263
An extension of ANOVA that compares how two or more continuous outcome variables vary according to categorical independent variables
MANOVA (Multivariate Analysis of Variance):
264
The maximum expected difference between a population parameter and a sample estimate
Margin of error:
265
A markup language that lets the user write formatted text in a coding environment or plain-text editor
Markdown:
266
A library for creating static, animated, and interactive visualizations in Python
matplotlib:
267
In tree-based models, a hyperparameter that controls how deep each base learner tree will grow
max_depth:
268
In decision tree and random forest models, a hyperparameter that specifies the number of features that each tree randomly selects during training called “colsample_bytree” in XGBoost
max_features:
269
A technique for estimating the beta parameters that maximizes the likelihood of the model producing the observed data
Maximum Likelihood Estimation (MLE):
270
The average value in a dataset
Mean:
271
A value that represents the center of a dataset
Measure of central tendency:
272
A value that represents the spread of a dataset, or the amount of variation in data points
Measure of dispersion:
273
A method by which the position of a value in relation to other values in a dataset is determined
Measure of position:
274
Numeric values that can be aggregated or placed in calculations
Measures:
275
The middle value in a dataset
Median:
276
Someone who shares knowledge, skills, and experience to help another grow both professionally and personally
Mentor:
277
A pandas function that joins two dataframes together; it only combines data by extending along axis one horizontally
merge():
278
A method to combine two (or more) different dataframes along a specified starting column(s)
Merging:
279
A function that belongs to a class and typically performs an action or operation
Method:
280
In XGBoost models, a hyperparameter indicating that a tree will not split a node if it results in any child node with less weight than this value called “min_samples_leaf” in decision tree and random forest models
min_child_weight:
281
Methods and criteria used to evaluate data
Metrics:
282
In decision tree and random forest models, a hyperparameter that defines the minimum number of samples for a leaf node called “min_child_weight” in XGBoost
min_samples_leaf:
282
In DBSCAN clustering models, a hyperparameter that specifies the number of samples in an ε-neighborhood for a point to be considered a core point (including itself)
min_samples:
283
In decision tree and random forest models, a hyperparameter that defines the minimum number of samples that a node must have to split into more nodes
min_samples_split:
284
A data value that is not stored for a variable in the observation of interest
Missing data:
285
The most frequently occurring value in a dataset
Mode:
286
Statements about the data that must be true in order to justify the use of a particular modeling technique
Model assumptions:
287
The process of determining which model should be the final product and put into production
Model selection:
288
The set of processes and activities intended to verify that models are performing as expected
Model validation:
289
The ability to write code in separate components that work together and that can be reused for other programs
Modularity:
290
A simple Python file containing a collection of functions and global variables
Module:
291
An operator that returns the remainder when one number is divided by another
Modulo:
292
A technique that estimates the relationship between one continuous dependent variable and two or more independent variables
Multiple linear regression:
292
The average of the squared difference between the predicted and actual values
MSE (Mean Squared Error):
293
(Refer to multiple linear regression)
Multiple regression:
294
The concept that if the events A and B are independent, then the probability of both A and B happening is the probability of A multiplied by the probability of B
Multiplication rule (for independent events):
295
The ability to change the internal state of a data structure
Mutability:
295
The concept that two events are mutually exclusive if they cannot occur at the same time
Mutually exclusive:
296
In K-means and agglomerative clustering models, a hyperparameter that specifies the number of clusters in the final model
n_clusters:
297
The core data object of NumPy; also referred to as “ndarray”
N-dimensional array:
298
In random forest and XGBoost models, a hyperparameter that specifies the number of trees your model will build in its ensemble
n_estimators:
299
A supervised classification technique that is based on Bayes’s Theorem with an assumption of independence among predictors
Naive Bayes:
300
Consistent guidelines that describe the content, creation date, and version of a file in its name
Naming conventions:
301
Rules built into the syntax of a programming language
Naming restrictions:
302
How null values are represented in pandas; stands for “not a number”
NaN:
303
A NumPy attribute used to check the number of dimensions of an array
ndim:
304
An inverse relationship between two variables, where when one variable increases, the other variable tends to decrease, and vice versa
Negative correlation:
305
A loop inside of another loop
Nested loop:
306
An assumption of simple linear regression stating that no two independent variables (Xi and Xj) can be highly correlated with each other
No multicollinearity assumption:
306
A group organized for purposes other than generating profit; often aims to further a social cause or provide a benefit to the public
Nonprofit:
307
A special data type in Python used to indicate that things are empty or that they return nothing
None:
307
The total number of data entries for a data column that are not blank
Non-null count:
307
A sampling method that is based on convenience or the personal preferences of the researcher, rather than random selection
Non-probability sampling:
307
A programming system that is based around objects which can contain both data and code that manipulates that data
Object-oriented programming:
307
Refers to when certain groups of people are less likely to provide responses
Nonresponse bias:
307
An assumption of simple linear regression stating that the residuals are normally distributed
Normality assumption:
307
A type of probability based on statistics, experiments, and mathematical measurements
Objective probability:
307
A continuous probability distribution that is symmetrical on both sides of the mean and bell-shaped
Normal distribution:
307
An essential library that contains multidimensional array and matrix data structures and functions to manipulate them
NumPy:
307
A component category, usually associated with its respective class
Object type:
307
A collection of data that consists of variables and methods or functions
Object:
308
The existing sample of data, where each data point in the sample is represented by an observed value of the dependent variable and an observed value of the independent variable
Observed values:
309
A data transformation technique that turns one categorical variable into several binary variables
One hot encoding:
310
(Refer to dependent variable)
Outcome variable (Y):
310
A type of statistical testing that compares the means of one continuous dependent variable based on three or more groups of one categorical variable
One-Way ANOVA:
310
Data that is available to the public and free to use, with guidance on how to navigate the datasets and acknowledge the source
Open data:
311
A common way to calculate linear regression coefficients
Ordinary least squares estimation (OLS):
312
Observations that are an abnormal distance from other values or an overall pattern in a data population
Outliers:
312
A way of combining data such that all of the keys from both dataframes get included in the merge
Outer join:
313
A message stating what to do next
Output:
314
When a model fits the observed or training data too specifically and is unable to generate suitable estimates for the general population
Overfitting:
315
The probability of observing results as extreme as those observed when the null hypothesis is true
P-value:
316
A workflow data professionals can use to remain focused on the end goal of any given dataset; stands for plan, analyze, construct, and execute
PACE:
317
A fundamental unit of shareable code that others have developed for a specific purpose
Package:
318
A powerful library built on top of NumPy that’s used to manipulate and analyze tabular data
pandas:
319
A characteristic of a population
Parameter:
320
The value below which a percentage of data falls
Percentile:
321
Information that permits the identity of an individual to be inferred by either direct or indirect means
Personally identifiable information (PII):
322
Stage of the PACE workflow where the scope of a project is defined and the informational needs of the organization are identified
Plan stage:
323
A calculation that uses a single value to estimate a population parameter
Point estimate:
324
A probability distribution that models the probability that a certain number of events will occur during a specific time period
Poisson distribution:
325
A method that extracts an element from a list by removing it at a given index
pop():
326
The phenomenon of more popular items being recommended too frequently
Popularity bias:
326
Every possible element that a data professional is interested in measuring
Population:
327
The percentage of individuals or elements in a population that share a certain characteristic
Population proportion:
328
A relationship between two variables that tend to increase or decrease together.
Positive correlation:
329
An ANOVA test that performs a pairwise comparison between all available groups while controlling for the error rate
Post hoc test:
330
The probability of an event occurring after taking into consideration new information
Posterior probability:
331
The proportion of positive predictions that were correct to all positive predictions
Precision:
332
The estimated Y values for each X calculated by a model
Predicted values:
333
(Refer to independent variable)
Predictor variable:
334
The process of making a cleaned dataset available to others for analysis or further modeling; one of the six practices of EDA
Presenting:
335
Refers to the probability of an event before new data is collected
Prior probability:
336
The branch of mathematics that deals with measuring and quantifying uncertainty
Probability:
337
A function that describes the likelihood of the possible outcomes of a random event
Probability distribution:
338
A sampling method that uses random selection to generate a sample
Probability sampling:
339
A series of instructions written so that a computer can perform a certain task, independent of any other application
Program:
340
The words and symbols used to write instructions for computers to follow
Programming languages:
341
A method of non-probability sampling that involves researchers selecting participants based on the purpose of their study
Purposive sample:
341
Measures the proportion of variation in the dependent variable, Y, explained by the independent variable(s), X
R2 (The Coefficient of Determination):
341
A general-purpose programming language
Python:
341
A value that divides a dataset into four equal parts
Quartile:
342
A visual that helps to define roles and responsibilities for individuals or teams to ensure work gets done efficiently; lists who is responsible, accountable, consulted, and informed for project tasks
RACI chart:
342
A process whose outcome cannot be predicted with certainty
Random experiment:
343
A starting point for generating random numbers
Random seed:
343
An ensemble of decision trees trained on bootstrapped data with randomly selected features
Random forest:
344
A Python function that returns a sequence of numbers starting from zero, increments by 1 by default, and stops before the given number
range():
344
A variable that represents the values for the possible outcomes of a random event
Random variable:
345
The difference between the largest and smallest value in a dataset
Range:
346
Unsupervised learning techniques that use unlabeled data to offer relevant suggestions to users
Recommendation systems:
346
The proportion of actual positives that were identified correctly to all actual positives
Recall:
347
The process of restructuring code while maintaining its original functionality
Refactoring:
348
A group of statistical techniques that use existing data to estimate the relationships between a single dependent variable and one or more independent variables
Regression analysis:
349
The estimated betas in a regression model
Regression coefficient:
350
A set of regression techniques that shrinks regression coefficient estimates towards zero, adding in bias, to reduce variance
Regularization:
350
(Refer to regression analysis)
Regression models:
351
A method that removes an element from a list
remove():
352
A sample that accurately reflects the characteristics of a population
Representative sample:
353
A NumPy method used to change the shape of an array
reshape():
354
The difference between observed or actual values and the predicted values of the regression line
Residual:
355
A reserved keyword in Python that makes a function produce new results which are saved for later use
return:
355
The capability to define code once and using it many times without having to rewrite it
Reusability:
356
(Refer to dependent variable)
Response variable:
357
A way of combining data such that all the keys in the right dataframe are included—even if they aren’t in the left dataframe
Right join:
358
The first node of the tree, where the first decision is made
Root node:
359
A segment of a population that is representative of the entire population
Sample:
360
The set of all possible values for a random variable
Sample space:
361
The number of individuals or items chosen for a study or experiment
Sample size:
362
The process of selecting a subset of data from a population
Sampling:
363
A probability distribution of a sample statistic
Sampling distribution:
363
Refers to when a sample is not representative of the population as a whole
Sampling bias:
364
A list of all the items in a target population
Sampling frame:
365
Refers to how much an estimate varies between samples
Sampling variability:
366
Refers to when a population element can be selected more than one time
Sampling with replacement:
367
Refers to when a population element can be selected only one time
Sampling without replacement:
368
A series of scatterplots that show the relationships between pairs of variables
Scatterplot matrix:
369
A collection of commands in a file designed to be executed like a program
Script:
370
A visualization library based on matplotlib that provides a simpler interface for working with common plots and graphs
Seaborn:
371
Data that was gathered outside your organization directly from the original source
Second-party data:
372
A parameter passed to a method or attributes used to instantiate an object
Self:
373
Code written in a way that is readable and makes its purpose clear
Self-documenting code:
374
A one-dimensional labeled array capable of holding any data type
Series:
374
Refers to the variables and objects that give meaning to Python code
Semantics:
374
A positionally-ordered collection of items
Sequence:
374
A function that takes an iterable as an argument and returns a new set object
Set():
374
A data structure in Python that contains only unordered, non-interchangeable elements; a Tableau term for a custom field of data created from a larger dataset based on custom conditions
Set:
374
A NumPy attribute used to check the shape of an array
shape:
374
The mean of the silhouette coefficients of all the observations in a model
Silhouette score:
375
A technique that estimates the linear relationship between one independent variable, X, and one continuous dependent variable, Y
Simple linear regression:
375
(Refer to learning_rate)
Shrinkage:
376
A probability sampling method in which every member of a population is selected randomly and has an equal chance of being chosen
Simple random sample:
377
The comparison of different models’ silhouette scores
Silhouette analysis:
378
A probability sampling method in which every member of a population is selected randomly and has an equal chance of being chosen
Simple random sample:
379
The minimum pairwise distance between clusters
Single:
380
A method for breaking information down into smaller parts to facilitate efficient examination and analysis from different viewpoints
Slicing:
381
The amount that y increases or decreases per one-unit increase of x
Slope:
382
A method of non-probability sampling that involves researchers recruiting initial participants to be in a study and then asking them to recruit other people to participate in the study
Snowball sample:
383
The process of arranging data into a meaningful order for analysis
Sorting:
384
A statistic that calculates the typical distance of a data point from the mean of a dataset
Standard deviation:
385
The standard deviation of a sample statistic
Standard error:
386
The sample standard deviation divided by the square root of the sample size
Standard error of the mean:
387
The square root of the sample proportion times one minus the sample proportion divided by the sample size
Standard error of the proportion:
388
The process of putting different variables on the same scale
Standardization:
389
A characteristic of a sample
Statistic:
390
The study of the collection, analysis, and interpretation of data
Statistics:
390
The claim that the results of a test or experiment are not explainable by chance alone
Statistical significance:
391
A probability sampling method that divides a population into groups and randomly selects some members from each group to be in the sample
Stratified random sample:
391
A Tableau term for a group of dashboards or worksheets assembled into a presentation
Story:
392
The portion of a string that can contain more than one character; also referred to as a substring
String slice:
393
A sequence of characters and punctuation that contains textual information
String:
393
A machine learning model that is used to make predictions about unseen events
Supervised model:
393
A programming string used in code in which characters exist as the value themselves, rather than as variables
String literal:
394
The sum of the squared difference between each observed value and its associated predicted value
Sum of squared residuals (SSR):
394
A type of probability based on personal feelings, experience, or judgment
Subjective probability:
394
A category of machine learning that uses labeled datasets to train algorithms to classify or predict outcomes
Supervised machine learning:
395
The process of taking raw data and organizing or transforming it to be more easily visualized, explained, or modeled; one of the six practices of EDA
Structuring:
396
A method that summarizes data using a single number
Summary statistics:
397
A function that finds elements from both sets that are mutually not present in the other
symmetric_difference():
397
The structure of code words, symbols, placement, and punctuation
Syntax:
398
A probability sampling method that puts every member of a population into an ordered sequence, chooses a random starting point in the sequence, and selects members for the sample at regular intervals
Systematic random sample:
399
A business intelligence and analytics platform that helps people visualize, understand, and make decisions with data
Tableau:
400
Data that is in the form of a table, with rows and columns
Tabular data:
401
The complete set of elements that someone is interested in knowing more about
Target population:
402
Data gathered outside your organization and aggregated
Third-party data:
402
A NumPy method to convert arrays into lists
Tolist():
403
A type of statistical testing that compares the means of one continuous dependent variable based on three or more groups of two categorical variables
Two-Way ANOVA:
403
A type of supervised machine learning that performs classification and regression tasks
Tree-based learning:
404
An immutable sequence that can contain elements of any data type
Tuple:
405
A function used to identify the type of data in a list
type():
406
A function that transforms input into tuples
tuple():
407
Refers to when some members of a population are inadequately represented in a sample
Undercoverage bias:
408
A machine learning model that is used to discover the natural structure of the data, finding relationships within unlabeled data
Unsupervised model:
408
A function that finds all the elements from both sets
union():
409
When constructing an interval, the calculation of the sample means plus the margin of error
Upper limit:
409
A named container which stores values in a reserved location in the computer’s memory
Variable:
410
The process of taking observations from the minority class and either adding copies of those observations to the dataset or generating new observations to add to the dataset
Upsampling:
411
The process of verifying that the data is consistent and high quality; one of the six practices of EDA
Validating:
412
A dictionary method to retrieve only the dictionary’s values
values():
413
The process of determining which variables or features to include in a given model
Variable selection:
414
Quantifies how correlated each independent variable is with all of the other independent variables
Variance inflation factors (VIF):
414
Refers to model flexibility and complexity, so the model learns from existing data; the average of the squared difference of each data point from the mean
Variance:
415
A process that enables operations to be performed on multiple components of a data object at the same time
Vectorization:
416
A method of non-probability sampling that consists of members of a population who volunteer to participate in a study
Voluntary response sample:
417
Merges two clusters whose merging will result in the lowest inertia
Ward:
418
A model that performs slightly better than randomly guessing
Weak learner:
419
A loop that instructs the computer to continuously execute the code based on the value of a condition
While loop:
420
An optimized GBM package
XGBoost (extreme gradient boosting):
421
Occurs when the dataset has no occurrences of a class label and some value of a predictor variable together
Zero Frequency problem:
422
A measure of how many standard deviations below or above the population mean a data point is
Z-score:
