SIA23 - Nominal Median and Nominal Mean Income Measures. Published by Central Statistics Office. Available under the license Creative Commons Attribution 4.0 (CC-BY-4.0).Nominal Median and Nominal Mean Income Measures...

Please note, this dataset has been superseded by a newer version (see below). Users should not use this version except in rare cases (e.g., when reproducing previous studies that used this version). Integrated Global Radiosonde Archive is a digital data set archived at the former National Climatic Data Center (NCDC), now National Centers for Environmental Information (NCEI). This dataset contains monthly means of geopotential height, temperature, zonal wind, and meridional wind derived from the Integrated Global Radiosonde Archive (IGRA). IGRA consists of radiosonde and pilot balloon observations at over 1500 globally distributed stations, and monthly means are available for the surface and mandatory levels at many of these stations. The period of record varies from station to station, with many extending from 1970 to 2016. Monthly means are computed separately for the nominal times of 0000 and 1200 UTC, considering data within two hours of each nominal time. A mean is provided, along with the number of values used to calculate it, whenever there are at least 10 values for a particular station, month, nominal time, and level.

TAH28 - Mean and Median equivalised nominal disposable income. Published by Central Statistics Office. Available under the license Creative Commons Attribution 4.0 (CC-BY-4.0).Mean and Median equivalised nominal disposable income...

The unit labour cost (ULC) is defined as the ratio of labour costs to labour productivity. Nominal ULC (NULC) = (D1/EEM) / (B1GQ/ETO) with D1 = Compensation of employees, all industries, current prices EEM = Employees, all industries, in persons (domestic concept) B1GQ = Gross domestic product at market prices in millions, chain-linked volumes reference year 2015 ETO = Total employment, all industries, in persons (domestic concept) The input data are obtained through official transmissions of national accounts' country data in the ESA 2010 transmission programme. The data are expressed as % change on previous year and as index 2015=100.

Refer to the current geographies boundaries table for a list of all current geographies and recent updates. This dataset is the definitive version of the annually released statistical area 2 (SA2) boundaries as at 1 January 2025 as defined by Stats NZ. This version contains 2,395 SA2s (2,379 digitised and 16 with empty or null geometries (non-digitised)). SA2 is an output geography that provides higher aggregations of population data than can be provided at the statistical area 1 (SA1) level. The SA2 geography aims to reflect communities that interact together socially and economically. In populated areas, SA2s generally contain similar sized populations. The SA2 should: form a contiguous cluster of one or more SA1s, excluding exceptions below, allow the release of multivariate statistics with minimal data suppression, capture a similar type of area, such as a high-density urban area, farmland, wilderness area, and water area, be socially homogeneous and capture a community of interest. It may have, for example: a shared road network, shared community facilities, shared historical or social links, or socio-economic similarity, ​ form a nested hierarchy with statistical output geographies and administrative boundaries. It must: be built from SA1s, either define or aggregate to define SA3s, urban areas, territorial authorities, and regional councils. SA2s in city council areas generally have a population of 2,000–4,000 residents while SA2s in district council areas generally have a population of 1,000–3,000 residents. In major urban areas, an SA2 or a group of SA2s often approximates a single suburb. In rural areas, rural settlements are included in their respective SA2 with the surrounding rural area. SA2s in urban areas where there is significant business and industrial activity, for example ports, airports, industrial, commercial, and retail areas, often have fewer than 1,000 residents. These SA2s are useful for analysing business demographics, labour markets, and commuting patterns. In rural areas, some SA2s have fewer than 1,000 residents because they are in conservation areas or contain sparse populations that cover a large area. To minimise suppression of population data, small islands with zero or low populations close to the mainland, and marinas are generally included in their adjacent land-based SA2. Zero or nominal population SA2s To ensure that the SA2 geography covers all of New Zealand and aligns with New Zealand’s topography and local government boundaries, some SA2s have zero or nominal populations. These include: SA2s where territorial authority boundaries straddle regional council boundaries. These SA2s each have fewer than 200 residents and are: Arahiwi, Tiroa, Rangataiki, Kaimanawa, Taharua, Te More, Ngamatea, Whangamomona, and Mara. SA2s created for single islands or groups of islands that are some distance from the mainland or to separate large unpopulated islands from urban areas SA2s that represent inland water, inlets or oceanic areas including: inland lakes larger than 50 square kilometres, harbours larger than 40 square kilometres, major ports, other non-contiguous inlets and harbours defined by territorial authority, and contiguous oceanic areas defined by regional council. SA2s for non-digitised oceanic areas, offshore oil rigs, islands, and the Ross Dependency. Each SA2 is represented by a single meshblock. The following 16 SA2s are held in non-digitised form (SA2 code; SA2 name): 400001; New Zealand Economic Zone, 400002; Oceanic Kermadec Islands, 400003; Kermadec Islands, 400004; Oceanic Oil Rig Taranaki, 400005; Oceanic Campbell Island, 400006; Campbell Island, 400007; Oceanic Oil Rig Southland, 400008; Oceanic Auckland Islands, 400009; Auckland Islands, 400010 ; Oceanic Bounty Islands, 400011; Bounty Islands, 400012; Oceanic Snares Islands, 400013; Snares Islands, 400014; Oceanic Antipodes Islands, 400015; Antipodes Islands, 400016; Ross Dependency. SA2 numbering and naming Each SA2 is a single geographic entity with a name and a numeric code. The name refers to a geographic feature or a recognised place name or suburb. In some instances where place names are the same or very similar, the SA2s are differentiated by their territorial authority name, for example, Gladstone (Carterton District) and Gladstone (Invercargill City). SA2 codes have six digits. North Island SA2 codes start with a 1 or 2, South Island SA2 codes start with a 3 and non-digitised SA2 codes start with a 4. They are numbered approximately north to south within their respective territorial authorities. To ensure the north–south code pattern is maintained, the SA2 codes were given 00 for the last two digits when the geography was created in 2018. When SA2 names or boundaries change only the last two digits of the code will change. ​ High-definition version This high definition (HD) version is the most detailed geometry, suitable for use in GIS for geometric analysis operations and for the computation of areas, centroids and other metrics. The HD version is aligned to the LINZ cadastre. ​ Macrons Names are provided with and without tohutō/macrons. The column name for those without macrons is suffixed ‘ascii’. ​ Digital data Digital boundary data became freely available on 1 July 2007. ​ Further information To download geographic classifications in table formats such as CSV please use Ariā For more information please refer to the Statistical standard for geographic areas 2023. Contact: geography@stats.govt.nz

Government debt (in millions EUR) is defined as the total consolidated gross debt at nominal value in the

following categories of government liabilities (as defined in ESA 2010): currency and deposits Dimension Categories ( (AF.2), debt securities (AF.3) and loans (AF.4)

Data Set Overview The Mars Express (MEX) Planetary Fourier Spectrometer (PFS) Data Archive is a collection of raw data collected during the MEX Mission to Mars. For more information on the investigations proposed see the PFS documentations in the DOCUMENT/ folder. This data set was collected during the MEX Mission phases: First Extension Mission Phase Mission Phase Definition It should be noted that the Mars Express (MEX) Planetary Fourier Spectrometer (PFS) group uses mission phases which deviate from the ones defined in the MISSION.CAT files given by ESA in order to keep the keywords and abbreviations consistent for Mars Express, Venus Express and Rosetta. Those mission phase abbreviations are also used in the data description field of the dataset_id. MaRS mission name | abbreviation | time span Near Earth Verification | NEV | 20030602 20030731 Interplanetary Cruise | IC | 20030801 20031225 Nominal Mission | Nominal | 20031226 20051130 First Extension Mission | EXT1 | 20060101 20070930 Second Extension Mission| EXT2 | 20071001 20091231 Data files Data files are: The tracking files from Deep Space Network (DSN) and from the Intermediate Frequency Modulation System (IFMS) used by the ESA ground station New Norcia. Level 1b data are archived. The Geometry files All Level binary data files will have the file name extension eee .DAT Data levels It should be noted that these data levels which are also used in the file names and data directories are PSA dat truncated!, Please see actual data for full text [truncated!, Please see actual data for full text]

SAMSN7L3ZMTG is the Nimbus-7 Stratospheric and Mesospheric Sounder (SAMS) Level 3 Zonal Means Composition Data Product. The Earth's surface is divided into 2.5-deg latitudinal zones that extend from 50 deg South to 67.5 deg North. Retrieved mixing ratios of nitrous oxide (N2O) and methane (CH4) are averaged over day and night, along with errors, at 31 pressure levels between 50 and 0.125 mbar. Because the N2O and CH4 channels cannot function simultaneously, only one type of measurement is made for any nominal day. The data were recovered from the original magnetic tapes, and are now stored online as one file in its original proprietary binary format. The data for this product are available from 1 January 1979 through 30 December 1981. The principal investigators for the SAMS experiment were Prof. John T. Houghton and Dr. Fredric W. Taylor from Oxford University. This product was previously available from the NSSDC with the identifier ESAD-00180 (old ID 78-098A-02C).

Refer to the current geographies boundaries table for a list of all current geographies and recent updates. This dataset is the definitive version of the annually released statistical area 3 (SA3) boundaries as at 1 January 2025 as defined by Stats NZ. This version contains 929 SA3s, including 4 non-digitised SA3s. The SA3 geography aims to meet three purposes: approximate suburbs in major, large, and medium urban areas, in predominantly rural areas, provide geographical areas that are larger in area and population size than SA2s but smaller than territorial authorities, minimise data suppression. SA3s in major, large, and medium urban areas were created by combining SA2s to approximate suburbs as delineated in the Fire and Emergency NZ (FENZ) Localities dataset. Some of the resulting SA3s have very large populations. Outside of major, large, and medium urban areas, SA3s generally have populations of 5,000–10,000. These SA3s may represent either a single small urban area, a combination of small urban areas and their surrounding rural SA2s, or a combination of rural SA2s. Zero or nominal population SA3s To minimise the amount of unsuppressed data that can be provided in multivariate statistical tables, SA2s with fewer than 1,000 residents are combined with other SA2s wherever possible to reach the 1,000 SA3 population target. However, there are still a number of SA3s with zero or nominal populations. Small population SA2s designed to maintain alignment between territorial authority and regional council geographies are merged with other SA2s to reach the 5,000–10,000 SA3 population target. These merges mean that some SA3s do not align with regional council boundaries but are aligned to territorial authority. Small population island SA2s are included in their adjacent land-based SA3. Island SA2s outside territorial authority or region are the same in the SA3 geography. Inland water SA2s are aggregated and named by territorial authority, as in the urban rural classification. Inlet SA2s are aggregated and named by territorial authority or regional council where the water area is outside the territorial authority. Oceanic SA2s translate directly to SA3s as they are already aggregated to regional council. The 16 non-digitised SA2s are aggregated to the following 4 non-digitised SA3s (SA3 code; SA3 name): 70001; Oceanic outside region, 70002; Oceanic oil rigs, 70003; Islands outside region, 70004; Ross Dependency outside region. SA3 numbering and naming Each SA3 is a single geographic entity with a name and a numeric code. The name refers to a suburb, recognised place name, or portion of a territorial authority. In some instances where place names are the same or very similar, the SA3s are differentiated by their territorial authority, for example, Hillcrest (Hamilton City) and Hillcrest (Rotorua District). SA3 codes have five digits. North Island SA3 codes start with a 5, South Island SA3 codes start with a 6 and non-digitised SA3 codes start with a 7. They are numbered approximately north to south within their respective territorial authorities. When first created in 2025, the last digit of each code was 0. When SA3 boundaries change in future, only the last digit of the code will change to ensure the north-south pattern is maintained. ​ High-definition version This high definition (HD) version is the most detailed geometry, suitable for use in GIS for geometric analysis operations and for the computation of areas, centroids and other metrics. The HD version is aligned to the LINZ cadastre. ​ Macrons Names are provided with and without tohutō/macrons. The column name for those without macrons is suffixed ‘ascii’. ​ Digital data Digital boundary data became freely available on 1 July 2007 ​ Further information To download geographic classifications in table formats such as CSV please use Ariā For more information please refer to the Statistical standard for geographic areas 2023. Contact: geography@stats.govt.nz

The financial indicators are based on data compiled according to the 2008 SNA "System of National Accounts, 2008". Many indicators are expressed as a percentage of Gross Domestic Product (GDP) or as a percentage of Gross Disposable Income (GDI) when referring to the Households and NPISHs sector. The definition of GDP and GDI are the following:

Gross Domestic Product:
Gross Domestic Product (GDP) is derived from the concept of value added. Gross value added is the difference of output and intermediate consumption. GDP is the sum of gross value added of all resident producer units plus that part (possibly the total) of taxes on products, less subsidies on products, that is not included in the valuation of output [System of National Accounts, 2008, par. 2.138]. GDP is also equal to the sum of final uses of goods and services (all uses except intermediate consumption) measured at purchasers’ prices, less the value of imports of goods and services [System of National Accounts, 2008, par. 2.139]. GDP is also equal to the sum of primary incomes distributed by producer units [System of National Accounts, 2008, par. 2.140].

Gross Disposable Income:
Gross Disposable Income (GDI) is equal to net disposable income which is the balancing item of the secondary distribution income account plus the consumption of fixed capital. The use of the Gross Disposable Income (GDI), rather than net disposable income, is preferable for analytical purposes because there are uncertainty and comparability problems with the calculation of consumption of fixed capital. GDI measures the income available to the total economy for final consumption and gross saving [System of National Accounts, 2008, par. 2.145].

Definition of Debt:
Debt is a commonly used concept, defined as a specific subset of liabilities identified according to the types of financial instruments included or excluded. Generally, debt is defined as all liabilities that require payment or payments of interest or principal by the debtor to the creditor at a date or dates in the future. Consequently, all debt instruments are liabilities, but some liabilities such as shares, equity and financial derivatives are not debt [System of National Accounts, 2008, par. 22.104]. According to the SNA, most debt instruments are valued at market prices. However, some countries do not apply this valuation, in particular for securities other than shares, except financial derivatives (AF33). In this dataset, for financial indicators referring to debt, the concept of debt is the one adopted by the SNA 2008 as well as by the International Monetary Fund in “Public Sector Debt Statistics – Guide for compilers and users” (Pre-publication draft, May 2011). Debt is thus obtained as the sum of the following liability categories, whenever available / applicable in the financial balance sheet of the institutional sector:special drawing rights (AF12), currency and deposits (AF2), debt securities (AF3), loans (AF4), insurance, pension, and standardised guarantees (AF6), and other accounts payable (AF8). This definition differs from the definition of debt applied under the Maastricht Treaty for European countries. First, gross debt according to the Maastricht definition excludes not only financial derivatives and employee stock options (AF7) and equity and investment fund shares (AF5) but also insurance pensions and standardised guarantees (AF6) and other accounts payable (AF8). Second, debt according to Maastricht definition is valued at nominal prices and not at market prices.

To view other related indicator datasets, please refer to:
Institutional Investors Indicators [add link]
Household Dashboard [add link]

Refer to the current geographies boundaries table for a list of all current geographies and recent updates. This dataset is the definitive version of the annually released statistical area 3 (SA3) boundaries as at 1 January 2025 as defined by Stats NZ, clipped to the coastline. This clipped version has been created for cartographic purposes and so does not fully represent the official full extent boundaries. This version contains 873 SA3s, excluding 4 non-digitised SA3s. The SA3 geography aims to meet three purposes: approximate suburbs in major, large, and medium urban areas, in predominantly rural areas, provide geographical areas that are larger in area and population size than SA2s but smaller than territorial authorities, minimise data suppression. SA3s in major, large, and medium urban areas were created by combining SA2s to approximate suburbs as delineated in the Fire and Emergency NZ (FENZ) Localities dataset. Some of the resulting SA3s have very large populations. Outside of major, large, and medium urban areas, SA3s generally have populations of 5,000–10,000. These SA3s may represent either a single small urban area, a combination of small urban areas and their surrounding rural SA2s, or a combination of rural SA2s. Zero or nominal population SA3s To minimise the amount of unsuppressed data that can be provided in multivariate statistical tables, SA2s with fewer than 1,000 residents are combined with other SA2s wherever possible to reach the 1,000 SA3 population target. However, there are still a number of SA3s with zero or nominal populations. Small population SA2s designed to maintain alignment between territorial authority and regional council geographies are merged with other SA2s to reach the 5,000–10,000 SA3 population target. These merges mean that some SA3s do not align with regional council boundaries but are aligned to territorial authority. Small population island SA2s are included in their adjacent land-based SA3. Island SA2s outside territorial authority or region are the same in the SA3 geography. Inland water SA2s are aggregated and named by territorial authority, as in the urban rural classification. Inlet SA2s are aggregated and named by territorial authority or regional council where the water area is outside the territorial authority. Oceanic SA2s translate directly to SA3s as they are already aggregated to regional council. The 16 non-digitised SA2s are aggregated to the following 4 non-digitised SA3s (SA3 code; SA3 name): 70001; Oceanic outside region, 70002; Oceanic oil rigs, 70003; Islands outside region, 70004; Ross Dependency outside region. SA3 numbering and naming Each SA3 is a single geographic entity with a name and a numeric code. The name refers to a suburb, recognised place name, or portion of a territorial authority. In some instances where place names are the same or very similar, the SA3s are differentiated by their territorial authority, for example, Hillcrest (Hamilton City) and Hillcrest (Rotorua District). SA3 codes have five digits. North Island SA3 codes start with a 5, South Island SA3 codes start with a 6 and non-digitised SA3 codes start with a 7. They are numbered approximately north to south within their respective territorial authorities. When first created in 2025, the last digit of each code was 0. When SA3 boundaries change in future, only the last digit of the code will change to ensure the north-south pattern is maintained. ​ Clipped Version This clipped version has been created for cartographic purposes and so does not fully represent the official full extent boundaries. ​ High-definition version This high definition (HD) version is the most detailed geometry, suitable for use in GIS for geometric analysis operations and for the computation of areas, centroids and other metrics. The HD version is aligned to the LINZ cadastre. ​ Macrons Names are provided with and without tohutō/macrons. The column name for those without macrons is suffixed ‘ascii’. ​ Digital data Digital boundary data became freely available on 1 July 2007. ​ Further information To download geographic classifications in table formats such as CSV please use Ariā For more information please refer to the Statistical standard for geographic areas 2023. Contact: geography@stats.govt.nz

This data set provides Machine Learning for defining breathing patterns in sleep for adults using preprocessed abdominal electromyograms (EMGs). The data set of 40 records was casually picked from a vaster database (Computing in Cardiology Challenge 2018: Training/Test Sets. 2018. URL: https://archive.physionet.org/physiobank/database/challenge/2018/). The optimal exponential smoothing model was uniform for all records: additive errors, small undamped trends, and no seasonality. Cleared out by trends and noises, signals had autocorrelation functions with the power-law decay. That has allowed making their persistence factors evaluations (Hurst exponent).
Most of the signals (38 of 40) showed frequent outliers: from a few percent up to 24.6 % of emissions. Wide data variability has been rated with the median absolute deviations, which is the most robust statistic in such a case. High variability looks a bit odd, considering low enough noise levels. The outliers' percentage, variability, SNR (signal-to-noise ratio), and persistency factors were statistically z-scored with medians and median absolute deviations. Further, their linear combinations form three independent Principal Components: numeric attributes z_1, z_2, and z_3 of the data set.
Manhattan distances matrix among subjects' vectors in 4D attributes space allows imaging the data set as a weighted biconnected graph, the vertices of which are subjects. The weights of the graph's edges reflect distances between any pair of them. "Closeness centralities" of vertices, a well-known parameter in graphs theory, allowed us to cluster the data on two clusters with 11 and 29 subjects. They present two biconnected subgraphs, peripheral and core, respectively. The belonging to one of them has been reflected in binary (nominal) attribute z_4. There are 0 as the label of the peripheral subgraph and 1 for core one, respectively. The periodograms of EMGs permitted us to find ten subjects with regular breathing and 30 with irregular one, defining two inequal classes using nominal attribute z_5. So, we offer here the data set for Machine Learning in ARFF format, containing 40 instances with five attributes, the sense of which is described above.

The Controlled Anomalies Time Series (CATS) Dataset consists of commands, external stimuli, and telemetry readings of a simulated complex dynamical system with 200 injected anomalies.

The CATS Dataset exhibits a set of desirable properties that make it very suitable for benchmarking Anomaly Detection Algorithms in Multivariate Time Series [1]:

Multivariate (17 variables) including sensors reading and control signals. It simulates the operational behaviour of an arbitrary complex system including:

4 Deliberate Actuations / Control Commands sent by a simulated operator / controller, for instance, commands of an operator to turn ON/OFF some equipment.

3 Environmental Stimuli / External Forces acting on the system and affecting its behaviour, for instance, the wind affecting the orientation of a large ground antenna.

10 Telemetry Readings representing the observable states of the complex system by means of sensors, for instance, a position, a temperature, a pressure, a voltage, current, humidity, velocity, acceleration, etc.

5 million timestamps. Sensors readings are at 1Hz sampling frequency.

1 million nominal observations (the first 1 million datapoints). This is suitable to start learning the "normal" behaviour.

4 million observations that include both nominal and anomalous segments. This is suitable to evaluate both semi-supervised approaches (novelty detection) as well as unsupervised approaches (outlier detection).

200 anomalous segments. One anomalous segment may contain several successive anomalous observations / timestamps. Only the last 4 million observations contain anomalous segments.

Different types of anomalies to understand what anomaly types can be detected by different approaches. The categories are available in the dataset and in the metadata.

Fine control over ground truth. As this is a simulated system with deliberate anomaly injection, the start and end time of the anomalous behaviour is known very precisely. In contrast to real world datasets, there is no risk that the ground truth contains mislabelled segments which is often the case for real data.

Suitable for root cause analysis. In addition to the anomaly category, the time series channel in which the anomaly first developed itself is recorded and made available as part of the metadata. This can be useful to evaluate the performance of algorithm to trace back anomalies to the right root cause channel.

Affected channels. In addition to the knowledge of the root cause channel in which the anomaly first developed itself, we provide information of channels possibly affected by the anomaly. This can also be useful to evaluate the explainability of anomaly detection systems which may point out to the anomalous channels (root cause and affected).

Obvious anomalies. The simulated anomalies have been designed to be "easy" to be detected for human eyes (i.e., there are very large spikes or oscillations), hence also detectable for most algorithms. It makes this synthetic dataset useful for screening tasks (i.e., to eliminate algorithms that are not capable to detect those obvious anomalies). However, during our initial experiments, the dataset turned out to be challenging enough even for state-of-the-art anomaly detection approaches, making it suitable also for regular benchmark studies.

Context provided. Some variables can only be considered anomalous in relation to other behaviours. A typical example consists of a light and switch pair. The light being either on or off is nominal, the same goes for the switch, but having the switch on and the light off shall be considered anomalous. In the CATS dataset, users can choose (or not) to use the available context, and external stimuli, to test the usefulness of the context for detecting anomalies in this simulation.

Pure signal ideal for robustness-to-noise analysis. The simulated signals are provided without noise: while this may seem unrealistic at first, it is an advantage since users of the dataset can decide to add on top of the provided series any type of noise and choose an amplitude. This makes it well suited to test how sensitive and robust detection algorithms are against various levels of noise.

No missing data. You can drop whatever data you want to assess the impact of missing values on your detector with respect to a clean baseline.

Change Log

Version 2

Metadata: we include a metadata.csv with information about:

Anomaly categories

Root cause channel (signal in which the anomaly is first visible)

Affected channel (signal in which the anomaly might propagate) through coupled system dynamics

Removal of anomaly overlaps: version 1 contained anomalies which overlapped with each other resulting in only 190 distinct anomalous segments. Now, there are no more anomaly overlaps.

Two data files: CSV and parquet for convenience.

[1] Example Benchmark of Anomaly Detection in Time Series: “Sebastian Schmidl, Phillip Wenig, and Thorsten Papenbrock. Anomaly Detection in Time Series: A Comprehensive Evaluation. PVLDB, 15(9): 1779 - 1797, 2022. doi:10.14778/3538598.3538602”

About Solenix

Solenix is an international company providing software engineering, consulting services and software products for the space market. Solenix is a dynamic company that brings innovative technologies and concepts to the aerospace market, keeping up to date with technical advancements and actively promoting spin-in and spin-out technology activities. We combine modern solutions which complement conventional practices. We aspire to achieve maximum customer satisfaction by fostering collaboration, constructivism, and flexibility.

Mammography is the most effective method for breast cancer screening available today. However, the low positive predictive value of breast biopsy resulting from mammogram interpretation leads to approximately 70% unnecessary biopsies with benign outcomes. To reduce the high number of unnecessary breast biopsies, several computer-aided diagnoses (CAD) systems have been proposed in the last years. These systems help physicians in their decision to perform a breast biopsy on a suspicious lesion seen in a mammogram or to perform a short-term follow-up examination instead.

This data set can be used to predict the severity (benign or malignant) of a mammographic mass lesion from BI-RADS attributes and the patient's age. It contains a BI-RADS assessment, the patient's age and three BI-RADS attributes together with the ground truth (the severity field).

Attribute Information: 1. BI-RADS assessment: 1 to 5 (ordinal, non-predictive!) 2. Age: patient's age in years (integer) 3. Shape: mass shape: round=1 oval=2 lobular=3 irregular=4 (nominal) 4. Margin: mass margin: circumscribed=1 microlobulated=2 obscured=3 ill-defined=4 spiculated=5 (nominal) 5. Density: mass density high=1 iso=2 low=3 fat-containing=4 (ordinal) 6. Severity: benign=0 or malignant=1 (binominal, goal field!)

Evaluation Task: Download the dataset from attached file and perform the following tasks: 1. Build Statistical Classification model to detect severity 2. What considerations have been used for model selection? 3. What features would you want to create for your prediction model based on data provided? 4. How have you performed hyper-parameter tuning and model optimization? What are the reasons for your decision choices for these steps? 5. What is your model evaluation criteria? What are the assumptions and limitations of your approach? 6. Determine whether the data is normally distributed visually and statistically. 7. Comment on EDA of variables in data. 8. How are you detecting and treating outliers in the dataset for better convergence? 9. What techniques have been used for treating missing values to prepare features for model building? 10. What is the distribution of target with respect to categorical columns? 11. Comment on any other observations or recommendations based on your analysis.

Refer to the current geographies boundaries table for a list of all current geographies and recent updates. This dataset is the definitive version of the annually released statistical area 2 (SA2) boundaries as at 1 January 2025 as defined by Stats NZ, clipped to the coastline. This clipped version has been created for cartographic purposes and so does not fully represent the official full extent boundaries. This clipped version contains 2,311 SA2 areas. SA2 is an output geography that provides higher aggregations of population data than can be provided at the statistical area 1 (SA1) level. The SA2 geography aims to reflect communities that interact together socially and economically. In populated areas, SA2s generally contain similar sized populations. The SA2 should: form a contiguous cluster of one or more SA1s, excluding exceptions below, allow the release of multivariate statistics with minimal data suppression, capture a similar type of area, such as a high-density urban area, farmland, wilderness area, and water area, be socially homogeneous and capture a community of interest. It may have, for example: a shared road network, shared community facilities, shared historical or social links, or socio-economic similarity, form a nested hierarchy with statistical output geographies and administrative boundaries. It must: be built from SA1s, either define or aggregate to define SA3s, urban areas, territorial authorities, and regional councils. SA2s in city council areas generally have a population of 2,000–4,000 residents while SA2s in district council areas generally have a population of 1,000–3,000 residents. In major urban areas, an SA2 or a group of SA2s often approximates a single suburb. In rural areas, rural settlements are included in their respective SA2 with the surrounding rural area. SA2s in urban areas where there is significant business and industrial activity, for example ports, airports, industrial, commercial, and retail areas, often have fewer than 1,000 residents. These SA2s are useful for analysing business demographics, labour markets, and commuting patterns. In rural areas, some SA2s have fewer than 1,000 residents because they are in conservation areas or contain sparse populations that cover a large area. To minimise suppression of population data, small islands with zero or low populations close to the mainland, and marinas are generally included in their adjacent land-based SA2. Zero or nominal population SA2s To ensure that the SA2 geography covers all of New Zealand and aligns with New Zealand’s topography and local government boundaries, some SA2s have zero or nominal populations. These include: SA2s where territorial authority boundaries straddle regional council boundaries. These SA2s each have fewer than 200 residents and are: Arahiwi, Tiroa, Rangataiki, Kaimanawa, Taharua, Te More, Ngamatea, Whangamomona, and Mara. SA2s created for single islands or groups of islands that are some distance from the mainland or to separate large unpopulated islands from urban areas SA2s that represent inland water, inlets or oceanic areas including: inland lakes larger than 50 square kilometres, harbours larger than 40 square kilometres, major ports, other non-contiguous inlets and harbours defined by territorial authority, and contiguous oceanic areas defined by regional council. SA2s for non-digitised oceanic areas, offshore oil rigs, islands, and the Ross Dependency. Each SA2 is represented by a single meshblock. The following 16 SA2s are held in non-digitised form (SA2 code; SA2 name): 400001; New Zealand Economic Zone, 400002; Oceanic Kermadec Islands, 400003; Kermadec Islands, 400004; Oceanic Oil Rig Taranaki, 400005; Oceanic Campbell Island, 400006; Campbell Island, 400007; Oceanic Oil Rig Southland, 400008; Oceanic Auckland Islands, 400009; Auckland Islands, 400010 ; Oceanic Bounty Islands, 400011; Bounty Islands, 400012; Oceanic Snares Islands, 400013; Snares Islands, 400014; Oceanic Antipodes Islands, 400015; Antipodes Islands, 400016; Ross Dependency. SA2 numbering and naming Each SA2 is a single geographic entity with a name and a numeric code. The name refers to a geographic feature or a recognised place name or suburb. In some instances where place names are the same or very similar, the SA2s are differentiated by their territorial authority name, for example, Gladstone (Carterton District) and Gladstone (Invercargill City). SA2 codes have six digits. North Island SA2 codes start with a 1 or 2, South Island SA2 codes start with a 3 and non-digitised SA2 codes start with a 4. They are numbered approximately north to south within their respective territorial authorities. To ensure the north–south code pattern is maintained, the SA2 codes were given 00 for the last two digits when the geography was created in 2018. When SA2 names or boundaries change only the last two digits of the code will change. ​ Clipped Version This clipped version has been created for cartographic purposes and so does not fully represent the official full extent boundaries. ​ High-definition version This high definition (HD) version is the most detailed geometry, suitable for use in GIS for geometric analysis operations and for the computation of areas, centroids and other metrics. The HD version is aligned to the LINZ cadastre. ​ Macrons Names are provided with and without tohutō/macrons. The column name for those without macrons is suffixed ‘ascii’. ​ Digital data Digital boundary data became freely available on 1 July 2007. Further information To download geographic classifications in table formats such as CSV please use Ariā For more information please refer to the Statistical standard for geographic areas 2023. Contact: geography@stats.govt.nz

The KNMI'23 climate scenarios are based on 240 years (8 ensembles of 30 years each) of RACMO (Regional Atmospheric Climate Model) v2.3 data for every horizon/scenario. The data in this set is a user-friendly version of the RACMO putput that was used to calculate the scenario tables. ‘User-friendly’ means that the data is mapped to a regular lat/lon grid, and that the time coordinate corresponds to the nominal period it is used for. This dataset version only includes values within the Dutch borders, for a more extensive area, please take a look at version 2 of this dataset (https://dataplatform.knmi.nl/dataset/knmi23-user-friendly-racmo-2-0). This user-friendly dataset is also provided to the public via the data portal. Additional information can be found in the KNMI’23 user report: https://cdn.knmi.nl/system/data_center_publications/files/000/071/901/original/KNMI23_klimaatscenarios_gebruikersrapport_23-03.pdf, as well as on the data portal: https://klimaatscenarios-data.knmi.nl/.

The Marine Environment Classification (MEC), a GIS-based environmental classification of the marine environment of the New Zealand region, is an ecosystem-based spatial framework designed for marine management purposes. Developed by NIWA with support from the Ministry for the Environment (MfE), Department of Conservation and Ministry of Fisheries, and with contributions from several other stakeholders, the MEC provides a spatial framework for inventories of marine resources, environmental effects assessments, policy development and design of protected area networks. Two levels of spatial resolution are available within the MEC. A broad scale classification covers the entire EEZ at a nominal spatial resolution of 1 km, whereas the finer scale classification of the Hauraki Gulf region has a nominal spatial resolution of 200 m. Several spatially-explicit data layers describing the physical environment define the MEC. A physically-based classification was chosen because data on these physical variables were available or could be modelled, and because the pattern of the physical environment is a reasonable surrogate for biological pattern, particularly at larger spatial scales. Classes within the classification were defined using multivariate clustering methods. These produce hierarchal classifications that enable the user to delineate environmental variation at different levels of detail and associated spatial scales. Large biological datasets were used to tune the classification, so that the physically-based classes maximised discrimination of variation in biological composition at various levels of classification detail. Thus, the MEC provides a general classification that is relevant to most groups of marine organisms (fishes, invertebrates and chlorophyll) and to ecologically important abiotic variables (e.g., temperature, nutrients).An overview report describing the MEC is available as a PDF file (External Link). The overview report covers the conceptual basis for the MEC and results of testing the classification: MEC Overview (PDF 2.7 MB)See here for a longer description: https://www.niwa.co.nz/coasts-and-oceans/our-services/marine-environment-classification_Item Page Created: 2018-11-12 22:47 Item Page Last Modified: 2019-07-24 03:58Owner: steinmetzt_NIWAExclusive Economic Zone (EEZ)No data edit dates availableFields: FID,ENTITY,LAYER,ELEVATION,THICKNESS,COLORMEC EEZ 40 classNo data edit dates availableFields: FID,GRP_40,COUNT_MEC EEZ 20 classNo data edit dates availableFields: FID,GRP_20,COUNT_MEC EEZ 10 classNo data edit dates availableFields: FID,GRP_10,COUNT_MEC EEZ 05 classNo data edit dates availableFields: FID,GRP_5,COUNT_CoastlineNo data edit dates availableFields: FID,NZCOAST_ID,SHAPE_LENG

Statistical Area 2 2023 update SA2 2023 is the first major update of the geography since it was first created in 2018. The update is to ensure SA2s are relevant and meet criteria before each five-yearly population and dwelling census. SA2 2023 contains 135 new SA2s. Updates were made to reflect real world change ofpopulation and dwelling growthmainly in urban areas, and to make some improvements to their delineation of communities of interest. ​ Description This dataset is the definitive version of the annually released statistical area 2 (SA2) boundaries as at 1 January 2023 as defined by Stats NZ (the custodian), clipped to the coastline. This clipped version has been created for cartographic purposes and so does not fully represent the official full extent boundaries. This clipped version contains 2,311 SA2 areas. SA2 is an output geography that provides higher aggregations of population data than can be provided at the statistical area 1 (SA1) level. The SA2 geography aims to reflect communities that interact together socially and economically. In populated areas, SA2s generally contain similar sized populations. ​ The SA2 should: form a contiguous cluster of one or more SA1s, excluding exceptions below, allow the release of multivariate statistics with minimal data suppression, capture a similar type of area, such as a high-density urban area, farmland, wilderness area, and water area, be socially homogeneous and capture a community of interest. It may have, for example: · a shared road network, · shared community facilities, · shared historical or social links, or · socio-economic similarity, form a nested hierarchy with statistical output geographies and administrative boundaries. It must: · be built from SA1s, · either define or aggregate to define SA3s, urban areas, territorial authorities, and regional councils. SA2s in city council areas generally have a population of 2,000–4,000 residents while SA2s in district council areas generally have a population of 1,000–3,000 residents. In major urban areas, an SA2 or a group of SA2s often approximates a single suburb. In rural areas, rural settlements are included in their respective SA2 with the surrounding rural area. SA2s in urban areas where there is significant business and industrial activity, for example ports, airports, industrial, commercial, and retail areas, often have fewer than 1,000 residents. These SA2s are useful for analysing business demographics, labour markets, and commuting patterns. In rural areas, some SA2s have fewer than 1,000 residents because they are in conservation areas or contain sparse populations that cover a large area. To minimise suppression of population data, small islands with zero or low populations close to the mainland, and marinas are generally included in their adjacent land-based SA2. ​ Zero or nominal population SA2s To ensure that the SA2 geography covers all of New Zealand and aligns with New Zealand’s topography and local government boundaries, some SA2s have zero or nominal populations. These include: · SA2s where territorial authority boundaries straddle regional council boundaries. These SA2s each have fewer than 200 residents and are: Arahiwi, Tiroa, Rangataiki, Kaimanawa, Taharua, Te More, Ngamatea, Whangamomona, and Mara. · SA2s created for single islands or groups of islands that are some distance from the mainland or to separate large unpopulated islands from urban areas · SA2s that represent inland water, inlets or oceanic areas including: inland lakes larger than 50 square kilometres, harbours larger than 40 square kilometres, major ports, other non-contiguous inlets and harbours defined by territorial authority, and contiguous oceanic areas defined by regional council. · SA2s for non-digitised oceanic areas, offshore oil rigs, islands, and the Ross Dependency. Each SA2 is represented by a single meshblock. The following 16 SA2s are held in non-digitised form (SA2 code; SA2 name): 400001; New Zealand Economic Zone, 400002; Oceanic Kermadec Islands, 400003; Kermadec Islands, 400004; Oceanic Oil Rig Taranaki, 400005; Oceanic Campbell Island, 400006; Campbell Island, 400007; Oceanic Oil Rig Southland, 400008; Oceanic Auckland Islands, 400009; Auckland Islands, 400010 ; Oceanic Bounty Islands, 400011; Bounty Islands, 400012; Oceanic Snares Islands, 400013; Snares Islands, 400014; Oceanic Antipodes Islands, 400015; Antipodes Islands, 400016; Ross Dependency. ​ SA2 numbering and naming Each SA2 is a single geographic entity with a name and a numeric code. The name refers to a geographic feature or a recognised place name or suburb. In some instances where place names are the same or very similar, the SA2s are differentiated by their territorial authority name, for example, Gladstone (Carterton District) and Gladstone (Invercargill City). SA2 codes have six digits. North Island SA2 codes start with a 1 or 2, South Island SA2 codes start with a 3 and non-digitised SA2 codes start with a 4. They are numbered approximately north to south within their respective territorial authorities. To ensure the north–south code pattern is maintained, the SA2 codes were given 00 for the last two digits when the geography was created in 2018. When SA2 names or boundaries change only the last two digits of the code will change. ​ For more information please refer to the Statistical standard for geographic areas 2023. ​ Macrons Names are provided with and without tohutō/macrons. The column name for those without macrons is suffixed ‘ascii’. Digital data Digital boundary data became freely available on 1 July 2007. ​ To download geographic classifications in table formats such as CSV please use Ariā