Time series
A time series is a sequence of observations indexed or ordered by time.
The Well-Grounded Data Analyst
A time series is a sequence of observations indexed by time, typically representing measurements collected across successive time points.
- How it is used
- Uses repeated measurements to investigate temporal patterns and support decisions such as infrastructure improvement or forecasting.
- How deep it goes
- Works through definition, data-quality checks, granularity, reshaping, visualization, decomposition, and forecast evaluation while deferring deeper forecasting algorithms.
- Examples
- Uses satisfaction scores, GDP, machine output, customer creation rates, and road traffic counts across measurement locations.
- What you can do after
- Evaluate/understand whether temporal data supports pattern analysis or forecasting after checking its structure, coverage, granularity, and gaps.
Read how The Well-Grounded Data Analyst explains time series →
Pandas Workout: 200 exercises to make you a stronger data analyst
A time series is a pandas data structure whose index contains timestamp values ordered or organized by time.
- How it is used
- Supports date-aware selection, interval slicing, resampling, and aggregation in pandas data analysis.
- How deep it goes
- Explains construction, partial-date indexing, inclusive slicing, and resampling, without descending into datetime implementation internals.
- Examples
- Uses historical oil prices, Apollo mission dates, and New York taxi tipping percentages as practical datasets.
- What you can do after
- Apply pandas date indexing and resampling to calculate period-specific statistics and compare observations across time.
Read how Pandas Workout: 200 exercises to make you a stronger data analyst explains time series →
Effective Data Analysis
A time series is a sequence of observations ordered or indexed by time points or intervals.
- How it is used
- Uses observations across time to visualize metrics, investigate historical behavior, and inform targets and stakeholder decisions.
- How deep it goes
- Explains time-based comparison, segmentation, aggregation, seasonality, and visualization risks, but stops short of forecasting methods.
- Examples
- Uses customer login activity by month, region, year, and active-day percentage, plus sales benchmarks and graduation-rate charts.
- What you can do after
- Evaluate trends by choosing interpretable charts, comparing segments, examining seasonality, and judging whether targets fit historical behavior.
Starting Data Analytics with Generative AI and Python
A time series is a sequence of observations indexed or ordered by time.
- How it is used
- Uses time-ordered observations to inspect business activity, data quality, operational phases, and potentially meaningful changes.
- How deep it goes
- Explains visualization, aggregation, cyclicity detection, and correlation risks, but stops short of forecasting or formal time-series modeling.
- Examples
- Demonstrates monthly review counts, daily and monthly review-score proportions, and review creation-to-answer time differences.
- What you can do after
- Diagnose/debug with it by visualizing temporal patterns, comparing aggregated periods, investigating delays, and validating suspicious observations.
Read how Starting Data Analytics with Generative AI and Python explains time series →
Outlier Detection in Python
A time series is a sequence of observations indexed by or ordered according to time.
- How it is used
- Supports outlier detection by preserving temporal order and revealing unusual fluctuations, trends, periodicity, and sequences.
- How deep it goes
- Defines time series, distinguishes related data structures, and demonstrates resampling, but stops short of advanced time-series modeling.
- Examples
- Uses UPS Twitter mentions, industrial temperature readings, and daily sales and purchase totals as concrete time-series examples.
- What you can do after
- Apply time-series representations to compare temporal behavior and construct simple anomaly checks.
MongoDB 8.0 in Action, Third Edition
Time-series data is a sequence of observations whose values are associated with timestamps and analyzed through changes over time.
- How it is used
- Stores timestamped measurements efficiently for sensors, stock prices, logs, and application performance metrics.
- How deep it goes
- Explains timestamps, metadata, measurements, bucketed BSON storage, and flat-model guidance without detailing advanced query design.
- Examples
- Uses sensor readings, stock prices, server logs, application metrics, and a MongoDB collection-creation command.
- What you can do after
- Operate/configure MongoDB time-series collections by assigning timestamp and metadata fields during creation.
Read how MongoDB 8.0 in Action, Third Edition explains time series →
ScyllaDB in Action
Time-series data is data associated with specific points or intervals in time, often subject to time-based expiration.
- How it is used
- Guides ScyllaDB compaction selection for data that expires according to time.
- How deep it goes
- Explains time association, expiration, time windows, and table configuration, without detailing broader time-series modeling.
- Examples
- Uses expiring data windows and TWCS compaction diagrams as concrete illustrations.
- What you can do after
- Operate ScyllaDB tables by selecting TWCS and configuring compaction through table properties or ALTER TABLE.
Causal Inference for Data Science
Time series data are observations indexed in temporal order, often collected at multiple time points.
- How it is used
- Deploys temporally ordered observations to describe change and estimate effects of time-related events.
- How deep it goes
- Defines the structure, contrasts related data types, and shows temporal graph unfolding, but defers a full theory for non-unfoldable directed cycles.
- Examples
- Uses film views, Google Trends, movie-release effects, price-demand dynamics, and simulated affected and comparison series.
- What you can do after
- Apply synthetic controls, regression discontinuity designs, or temporal graph unfolding to analyze event effects and counterfactual outcomes.
Read how Causal Inference for Data Science explains time series →
Elasticsearch in Action, Second Edition
Time-series data consists of observations associated with timestamps or time intervals, usually ordered chronologically.
- How it is used
- Handles timestamped, continuously accumulating records through rollover-aware indexing and unified search access.
- How deep it goes
- Defines time dependence and outlines rollover, aliases, and data streams, but does not detail implementation commands.
- Examples
- Uses Apache web-server logs, daily files, midnight rollover, rolling indexes, aliases, and automatically generated hidden indexes.
- What you can do after
- Operate time-series storage by planning periodic index rollover and searching rolling indexes through an alias or data stream.
Read how Elasticsearch in Action, Second Edition explains time series →
Related concepts
- data framekind of · A data frame is a two-dimensional tabular data structure with labeled rows and columns that can contain values of different types.
- Prometheusused by · Prometheus is an open-source monitoring and alerting system that collects, stores, and queries time-series metrics.
- timestamphas part · A timestamp is a value representing a specific point in time, typically associated with an event, observation, or data item.
- measurementhas part · Measurement is the systematic assessment of a property, behavior, or outcome that produces an observed value, score, or judgment.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.