Index
A
Activation maps
activation
training
web-based UI
AI/ML models
Algorithmic complexity
deep learning network
image data, cubic-complexity
regression model
relative growth comparison
Apache Arrow columnar memory format
Artificial intelligence (AI)
Aspiring data
.at or .iloc methods
AutoML tools
B
Back-end processing
Base class
Basic web technologies
Best-matching distribution
datasets
plot
simple fitting
Binary search
Boolean filters
Business and technological enterprises
C
Cell magic
Classification score
Client-scheduler-worker
Cloud computing technologies
Cloud instance
Cloud technology
Colab Pro
ColDrop method
Computing
Containers technologies
Convolutional neural network (CNN)
cProfile library
array operations
data science workflow
Profiler class
usage
cProfile.run function
Cross-validation (CV)
CSV analysis app
CSV analysis web app
CUDA programming
CUDA version
CuDF DataFrame
CuDF vs. pandas
CuGraph
CuML pipeline
CuML version
CuPy algorithm
NumPy comparison
interface
usage
D
Dask
array
bag
clusters
dashboard
DataFrame
distributed client
hood
ML
tasks
Dask Future
dask-ml library
Data-as-a-Service (DaaS)
Database technologies
Database knowledge
DataOps architectures
Data/problem scaling
Data repository
Data scaling challenge
Data science
brute-force for loop
combinatorial sign
definition
generic function
inefficient programming
canonical example
computing tasks
iterrows()
pandas DataFrame
pitfalls
GUI programming/web app development
hardware/traditional tools
measure efficiency
measuring efficiency
ML model development
modularized and expressive data science pipeline
OOP
productive data
Python
unit/functional testing
plotting code
Python libraries
scatterplot
task flow
test module
tools
workflow stages
Data science methods
Data science pipeline
Data scientist
arithmetic
OOP
Datasets
Decision boundary visualization
Deep learning (DL)
Deep neural network (DNN)
DevOps
distfit library
Docker Engine
E
Elastic Compute (EC2) instance
eval method
Evaluation metrics
Execution time
Jupyter/IPython magic command
Pythons time module
Extend class functionality
F
Filtering operation
fit_generator method
fit_transform method
Flask
Flask app files
Flask ML prediction app
G
Gigabytes (GB)
Global Interpreter Lock (GIL)
Goodness-of-fit (GOF)
Google Cloud Platform (GCP)
Google Colaboratory
GPU-accelerated data science
GPU memory
GPU-powered hardware
Graphics processing unit (GPU)
GUI/app development
H
Hardware story
AI and ML solutions
hardware development
Hidden gems
Hyperparameter
cross-validation
data/keras model
grid search
kerasClassifier class
scikit-learn library
I
Image classification
CNN
data generator object
dataset
encapsulate
extensions
fit_generator method
image dataset
simplifying
testing utility function
Imposter syndrome
Income range prediction model
Informed search
Infrastructure-as-a-Service (IaaS)
J
JavaScript library
Job interview
Jump-starter packages
Jupyter magic commands
Jupyter notebook
K
Keract
Keras callback class
k-means algorithm
K-means clustering
K-nearest neighbor (KNN)
Kubernetes
L
Linear regression algorithm
Linear search
Line command
Low-cardinality data
Low-code libraries
M
Machine learning (ML)
algorithms
data scale
deep learning
experiments
final validation
key advice
linear regression
modular code
standard data science task flow
systematic evaluation
systematic evaluation, automation
Mathematical operators
Matplotlib and Seaborn
Memory profile
mljar-mercury
MLOps
Model compression
Model scaling challenge
Modern data science
Modern ML systems
Modin
features
out-of-core processing
single CPU
Modular Code
fast experimentation
business/data science
compile/train functions
final code
keras callback
utility functions
visualization function
OOP
builders
callbacks
DL task
wrapper
Multiple terabytes (TB)
N
Natural language processing (NLP)
N-dimensional numerical arrays
ne.evaluate() function
Neural network model
NLTK tokenizer method
NoSQL technologies
Numerical Python
Numexpr method
Numexpr package
NumPy
.append method
arithmetic
arrays
array size
arrays vs. native python computation
Boolean filters
built-in vectorize function
chaining methods
complex numbers
complex operation
conversion first/operation later
definition
libraries
logical operators
pandas productivity
reading utilities
remove orphan dataframes
vectorize logical operations
NumPy operations
NumPy package
O
Object-oriented programming (OOP)
modularization
separate plotting classes
supporting classes
Out-of-core datasets
P
Pandas
DataFrame
documentation
eval method
Pandas-specific tricks
column-specific functions
convert data
loading function
Paperspace Gradient
Parallel computing
data science
single core
Parallel processing
pd.eval() method
pdpipe
dataset
laying pipes
chain stages
dropping rows
NLTK
scikit-learn
pip command
Platform-as-a-Service (PaaS)
plot command
predict method
Productive data science work
PyArrow
PyCaret
PyPi installer package
code organizational thinking
GitHub
unit/functional tests
writing docstrings
Python app
Python-based data science
Python data science ecosystem
Python language
Python libraries
Python package
GitHub integration
instructions
Python processing
Python programs
Python script
PyWebIO library
Q
Quantile-quantile plot
Quiver
R
Race dropdown choices
Random Forest
RAPIDS ecosystem
advantage
CUDA
data preparation and wrangling tasks
data processing
fantastic ecosystem
internal support
Jupyter server
libraries and APIs
parallelism
RAPIDS environment
Ray
data science
dataset
distributed data transformations
ecosystems
VM
Real-life analytics problem
Residuals
S
Saturn Cloud platform
Scalability problems
Scalene
CLI
features
output
usage
Scikit-learn
hyperparameters
out-of-box visualization methods
parallel job runner
synthetic data generators
Scikit-learn Task Flow
Scripting
Single-threaded programs
Singular value decomposition (SVD)
Software engineering practices
Static snapshot
Support Vector Machine (SVM)
T
Task scheduling
Testing software modules
Time and space complexities
Big-O notation
binary search
linear time
searching element
worst-case
U
Useless class
fitting method
prediction method
testing method
testing prediction
Utility functions
Utility method
error metrics
plotting true vs. predicted values
V
Vaex library
dynamic visualizations
expressions/virtual columns
features
HDF5 format
memory copying
multidimensional grid
usage
ValDrop method
Vector registers
Virtual machine (VM)
Visualization function
W, X, Y, Z
Web apps
Windows OS
Wrapper functions
Wrapping up
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.