Imports:

# All Imports
import os
from matplotlib import pyplot as plt
import pandas as pd
from sklearn.calibration import LabelEncoder
import seaborn as sns
import matplotlib.image as mpimg
import cv2
import numpy as np
import pickle

# Tensflor and Keras Layer and Model and Optimize and Loss
import tensorflow as tf
from tensorflow import keras
from keras import Sequential
from keras.layers import *

#Kernel Intilizer 
from keras.optimizers import Adamax

# PreTrained Model
from keras.applications import *

#Early Stopping
from keras.callbacks import EarlyStopping
import warnings 

Warnings Suppression | Configuration

# Warnings Remove 
warnings.filterwarnings("ignore")

# Define the base path for the training folder
base_path = 'jaguar_cheetah/train'

# Weights file
weights_file = 'Model_train_weights.weights.h5'

# Path to the saved or to save the model:
model_file = 'Model-cheetah_jaguar_Treined.keras'

# Model history
history_path = 'training_history_cheetah_jaguar.pkl'

# Initialize lists to store file paths and labels
filepaths = []
labels = []

# Iterate over folders and files within the training directory
for folder in ['Cheetah', 'Jaguar']:
  folder_path = os.path.join(base_path, folder)
  for filename in os.listdir(folder_path):
    file_path = os.path.join(folder_path, filename)
    filepaths.append(file_path)
    labels.append(folder)

# Create the TRAINING dataframe
file_path_series = pd.Series(filepaths , name= 'filepath')
Label_path_series = pd.Series(labels , name = 'label')
df_train = pd.concat([file_path_series ,Label_path_series ] , axis = 1)


# Define the base path for the test folder
directory = "jaguar_cheetah/test"

filepath =[]
label = []

folds = os.listdir(directory)

for fold in folds:
  f_path = os.path.join(directory , fold)
  
  imgs = os.listdir(f_path)
  
  for img in imgs:
    
    img_path = os.path.join(f_path , img)
    filepath.append(img_path)
    label.append(fold)
    
# Create the TEST dataframe
file_path_series = pd.Series(filepath , name= 'filepath')
Label_path_series = pd.Series(label , name = 'label')
df_test = pd.concat([file_path_series ,Label_path_series ] , axis = 1)

# Display the first rows of the dataframe for verification
#print(df_train)

# Folders with Training and Test files
data_dir = 'jaguar_cheetah/train'
test_dir = 'jaguar_cheetah/test'

# Image size 256x256
IMAGE_SIZE = (256,256) 

Tain | Test

#print('Training Images:')

# Create the TRAIN dataframe
train_ds = tf.keras.utils.image_dataset_from_directory(
  data_dir,
  validation_split=0.1,
  subset='training',
  seed=123,
  image_size=IMAGE_SIZE,
  batch_size=32)

#Testing Data
#print('Validation Images:')
validation_ds = tf.keras.utils.image_dataset_from_directory(
  data_dir, 
  validation_split=0.1,
  subset='validation',
  seed=123,
  image_size=IMAGE_SIZE,
  batch_size=32)

print('Testing Images:')
test_ds = tf.keras.utils.image_dataset_from_directory(
  test_dir, 
  seed=123,
  image_size=IMAGE_SIZE,
  batch_size=32)

# Extract labels
train_labels = train_ds.class_names
test_labels = test_ds.class_names
validation_labels = validation_ds.class_names

# Encode labels
# Defining the class labels
class_labels = ['CHEETAH', 'JAGUAR'] 

# Instantiate (encoder) LabelEncoder
label_encoder = LabelEncoder()

# Fit the label encoder on the class labels
label_encoder.fit(class_labels)

# Transform the labels for the training dataset
train_labels_encoded = label_encoder.transform(train_labels)

# Transform the labels for the validation dataset
validation_labels_encoded = label_encoder.transform(validation_labels)

# Transform the labels for the testing dataset
test_labels_encoded = label_encoder.transform(test_labels)

# Normalize the pixel values

# Train files 
train_ds = train_ds.map(lambda x, y: (x / 255.0, y))
# Validate files
validation_ds = validation_ds.map(lambda x, y: (x / 255.0, y))
# Test files
test_ds = test_ds.map(lambda x, y: (x / 255.0, y))

#TRAINING VISUALIZATION
#Count the occurrences of each category in the column
count = df_train['label'].value_counts()

# Create a figure with 2 subplots
fig, axs = plt.subplots(1, 2, figsize=(12, 6), facecolor='white')

# Plot a pie chart on the first subplot
palette = sns.color_palette("viridis")
sns.set_palette(palette)
axs[0].pie(count, labels=count.index, autopct='%1.1f%%', startangle=140)
axs[0].set_title('Distribution of Training Categories')

# Plot a bar chart on the second subplot
sns.barplot(x=count.index, y=count.values, ax=axs[1], palette="viridis")
axs[1].set_title('Count of Training Categories')

# Adjust the layout
plt.tight_layout()

# Visualize
plt.show()

# TEST VISUALIZATION
count = df_test['label'].value_counts()

# Create a figure with 2 subplots
fig, axs = plt.subplots(1, 2, figsize=(12, 6), facec...

Advances in neuroimaging, genomic, motion tracking, eye-tracking and many other technology-based data collection methods have led to a torrent of high dimensional datasets, which commonly have a small number of samples because of the intrinsic high cost of data collection involving human participants. High dimensional data with a small number of samples is of critical importance for identifying biomarkers and conducting feasibility and pilot work, however it can lead to biased machine learning (ML) performance estimates. Our review of studies which have applied ML to predict autistic from non-autistic individuals showed that small sample size is associated with higher reported classification accuracy. Thus, we have investigated whether this bias could be caused by the use of validation methods which do not sufficiently control overfitting. Our simulations show that K-fold Cross-Validation (CV) produces strongly biased performance estimates with small sample sizes, and the bias is still evident with sample size of 1000. Nested CV and train/test split approaches produce robust and unbiased performance estimates regardless of sample size. We also show that feature selection if performed on pooled training and testing data is contributing to bias considerably more than parameter tuning. In addition, the contribution to bias by data dimensionality, hyper-parameter space and number of CV folds was explored, and validation methods were compared with discriminable data. The results suggest how to design robust testing methodologies when working with small datasets and how to interpret the results of other studies based on what validation method was used.

The MS Training Set, MS Validation Set, and UW Validation/Test Set are used for training, validation, and testing the proposed methods.

This dataset consists of the synthetic electron backscatter diffraction (EBSD) maps generated for the paper, titled "Hybrid Algorithm for Filling in Missing Data in Electron Backscatter Diffraction Maps" by Emmanuel Atindama, Conor Miller-Lynch, Huston Wilhite, Cody Mattice, Günay Doğan, and Prashant Athavale. The EBSD maps were used to train, test, and validate a neural network algorithm to fill in missing data points in a given EBSD map.The dataset includes 8000 maps for training, 1000 maps for testing, 2000 maps for validation. The dataset also includes noise-added versions of the maps, namely, one more map per each clean map.

Your goal

Train a machine learning model based on the runtime data provided to you in the training dataset and further predict the runtime of graphs and configurations in the test dataset.

For Data understanding , EDA and Baseline model you can refer to my notebook

https://www.kaggle.com/code/rishabh15virgo/first-impression-understand-data-eda-baseline-15

Training and Test dataset:

Train Dataset :

https://www.kaggle.com/datasets/rishabh15virgo/google-fast-or-slowtile-xla-train-data-csv-format

Test Dataset :

https://www.kaggle.com/datasets/rishabh15virgo/google-fast-or-slowtile-xla-test-data-csv-format

Data Information

Tile .npz files Suppose a .npz file stores a graph (representing a kernel) with n nodes and m edges. In addition, suppose we compile the graph with c different configurations, and run each on a TPU. Crucially, the configuration is at the graph-level. Then, the .npz file stores the following dictionary

Key "node_feat": contains float32 matrix with shape (n, 140). The uth row contains the feature vector for node u < n . Nodes are ordered topologically. Key "node_opcode" contains int32 vector with shape (n, ). The uth entry stores the op-code for node u. Key **"edge_index" **contains int32 matrix with shape (m, 2). If entry i is = u, v, then there is a directed edge from node u to node v, where u consumes the output of v. Key "config_feat" contains float32 matrix with shape (c, 24) with row j containing the (graph-level) configuration feature vector. Keys "config_runtime" and "config_runtime_normalizers": both are int64 vectors of length c. Entry j stores the runtime (in nanoseconds) of the given graph compiled with configuration j and a default configuration, respectively. Samples from the same graph may have slightly different "config_runtime_normalizers" because they are measured from different runs on multiple machines. Finally, for the tile collection, your job is to predict the indices of the best configurations (i.e., ones leading to the smallest d["config_runtime"] / d["config_runtime_normalizers"]).

Formats1.xlsx contains the descriptions of the columns of the following datasets: Training, validation and test datasets in combination are all the records.sens1.csv and and meansdX.csv are required for testing.

This dataset is a split version of the original Image-dataset found here. The dataset consists of 8 emotion classes: angry, contempt, disgust, fear, happiness, neutral, sadness, and surprise.

To facilitate model training and evaluation, I have organized the dataset into three subsets:

Train: Used for training machine learning models. Test: Used to evaluate model performance after training. Validation: Used during training to tune hyperparameters and prevent overfitting.

This split allows for more effective usage in tasks such as Facial Emotion Recognition (FER) and other emotion analysis projects.

This dataset describes the training, validation and test dataset used for the development of a hybrid ANN coagulation model.

This is the database for full model training and evaluation for LPM

Splits of train, test, and validation samples for Urban dataset.

This record contains the training, test and validation datasets used to train and evaluate the machine learning models in manuscript:

Sahu, Biswajyoti, et al. "Sequence determinants of human gene regulatory elements." (2021).

This record contains also the final hyperparameter-optimized models for each training dataset/task combination described in the manuscript. The README-files provided with the record describe the datasets and models in more detail. The datasets deposited here are derived from the original raw data (GEO accession: GSE180158) as described in the Methods of the manuscript.

Bats play crucial ecological roles and provide valuable ecosystem services, yet many populations face serious threats from various ecological disturbances. The North American Bat Monitoring Program (NABat) aims to assess status and trends of bat populations while developing innovative and community-driven conservation solutions using its unique data and technology infrastructure. To support scalability and transparency in the NABat acoustic data pipeline, we developed a fully-automated machine-learning algorithm. This dataset includes audio files of bat echolocation calls that were considered to develop V1.0 of the NABat machine-learning algorithm, however the test set (i.e., holdout dataset) has been excluded from this release. These recordings were collected by various bat monitoring partners across North America using ultrasonic acoustic recorders for stationary acoustic and mobile acoustic surveys. For more information on how these surveys may be conducted, see Chapters 4 and 5 of “A Plan for the North American Bat Monitoring Program” (https://doi.org/10.2737/SRS-GTR-208). These data were then post-processed by bat monitoring partners to remove noise files (or those that do not contain recognizable bat calls) and apply a species label to each file. There is undoubtedly variation in the steps that monitoring partners take to apply a species label, but the steps documented in “A Guide to Processing Bat Acoustic Data for the North American Bat Monitoring Program” (https://doi.org/10.3133/ofr20181068) include first processing with an automated classifier and then manually reviewing to confirm or downgrade the suggested species label. Once a manual ID label was applied, audio files of bat acoustic recordings were submitted to the NABat database in Waveform Audio File format. From these available files in the NABat database, we considered files from 35 classes (34 species and a noise class). Files for 4 species were excluded due to low sample size (Corynorhinus rafinesquii, N=3; Eumops floridanus, N =3; Lasiurus xanthinus, N = 4; Nyctinomops femorosaccus, N =11). From this pool, files were randomly selected until files for each species/grid cell combination were exhausted or the number of recordings reach 1250. The dataset was then randomly split into training, validation, and test sets (i.e., holdout dataset). This data release includes all files considered for training and validation, including files that had been excluded from model development and testing due to low sample size for a given species or because the threshold for species/grid cell combinations had been met. The test set (i.e., holdout dataset) is not included. Audio files are grouped by species, as indicated by the four-letter species code in the name of each folder. Definitions for each four-letter code, including Family, Genus, Species, and Common name, are also included as a dataset in this release.

Dataset Description

Context and Methodology

• Research Domain/Project:
  This dataset was created for a machine learning experiment aimed at developing a classification model to predict outcomes based on a set of features. The primary research domain is disease prediction in patients. The dataset was used in the context of training, validating, and testing.

• Purpose of the Dataset:
  The purpose of this dataset is to provide training, validation, and testing data for the development of machine learning models. It includes labeled examples that help train classifiers to recognize patterns in the data and make predictions.

• Dataset Creation:
  Data preprocessing steps involved cleaning, normalization, and splitting the data into training, validation, and test sets. The data was carefully curated to ensure its quality and relevance to the problem at hand. For any missing values or outliers, appropriate handling techniques were applied (e.g., imputation, removal, etc.).

Technical Details

• Structure of the Dataset:
  The dataset consists of several files organized into folders by data type:

  • Training Data: Contains the training dataset used to train the machine learning model.

  • Validation Data: Used for hyperparameter tuning and model selection.

  • Test Data: Reserved for final model evaluation.

  Each folder contains files with consistent naming conventions for easy navigation, such as train_data.csv, validation_data.csv, and test_data.csv. Each file follows a tabular format with columns representing features and rows representing individual data points.

• Software Requirements:
  To open and work with this dataset, you need VS Code or Jupyter, which could include tools like:

  • Python (with libraries such as pandas, numpy, scikit-learn, matplotlib, etc.)

Further Details

• Reusability:
  Users of this dataset should be aware that it is designed for machine learning experiments involving classification tasks. The dataset is already split into training, validation, and test subsets. Any model trained with this dataset should be evaluated using the test set to ensure proper validation.

• Limitations:
  The dataset may not cover all edge cases, and it might have biases depending on the selection of data sources. It's important to consider these limitations when generalizing model results to real-world applications.

File Validation and Training Statistics

Validation, Training, and Testing Statistics for tasksource/leandojo Files

By tasksource (From Huggingface) [source]

About this dataset

The tasksource/leandojo: File Validation, Training, and Testing Statistics dataset is a comprehensive collection of information regarding the validation, training, and testing processes of files in the tasksource/leandojo repository. This dataset is essential for gaining insights into the file management practices within this specific repository.

The dataset consists of three distinct files: validation.csv, train.csv, and test.csv. Each file serves a unique purpose in providing statistics and information about the different stages involved in managing files within the repository.

In validation.csv, you will find detailed information about the validation process undergone by each file. This includes data such as file paths within the repository (file_path), full names of each file (full_name), associated commit IDs (commit), traced tactics implemented (traced_tactics), URLs pointing to each file (url), and respective start and end dates for validation.

train.csv focuses on providing valuable statistics related to the training phase of files. Here, you can access data such as file paths within the repository (file_path), full names of individual files (full_name), associated commit IDs (commit), traced tactics utilized during training activities (traced_tactics), URLs linking to each specific file undergoing training procedures (url).

Lastly, test.csv encompasses pertinent statistics concerning testing activities performed on different files within the tasksource/leandojo repository. This data includes information such as file paths within the repo structure (file_path), full names assigned to each individual file tested (full_name) , associated commit IDs linked with these files' versions being tested(commit) , traced tactics incorporated during testing procedures regarded(traced_tactics) ,relevant URLs directing to specific tested files(url).

By exploring this comprehensive dataset consisting of three separate CSV files - validation.csv, train.csv, test.csv - researchers can gain crucial insights into how effective strategies pertaining to validating ,training or testing tasks have been implemented in order to maintain high-quality standards within the tasksource/leandojo repository

How to use the dataset

• Familiarize Yourself with the Dataset Structure:

  • The dataset consists of three separate files: validation.csv, train.csv, and test.csv.
  • Each file contains multiple columns providing different information about file validation, training, and testing.

• Explore the Columns:

  • 'file_path': This column represents the path of the file within the repository.
  • 'full_name': This column displays the full name of each file.
  • 'commit': The commit ID associated with each file is provided in this column.
  • 'traced_tactics': The tactics traced in each file are listed in this column.
  • 'url': This column provides the URL of each file.

• Understand Each File's Purpose:

Validation.csv - This file contains information related to the validation process of files in the tasksource/leandojo repository.

Train.csv - Utilize this file if you need statistics and information regarding the training phase of files in tasksource/leandojo repository.

Test.csv - For insights into statistics and information about testing individual files within tasksource/leandojo repository, refer to this file.

• Generate Insights & Analyze Data:
• Once you have a clear understanding of each column's purpose, you can start generating insights from your analysis using various statistical techniques or machine learning algorithms.

• Explore patterns or trends by examining specific columns such as 'traced_tactics' or analyzing multiple columns together.

• Combine Multiple Files (if necessary):

• If required, you can merge/correlate data across different csv files based on common fields such as 'file_path', 'full_name', or 'commit'.

• Visualize the Data (Optional):

• To enhance your analysis, consider creating visualizations such as plots, charts, or graphs. Visualization can offer a clear representation of patterns or relationships within the dataset.

• Obtain Further Information:

• If you need additional details about any specific file, make use of the provided 'url' column to access further information.

Remember that this guide provides a general overview of how to utilize this dataset effectively. Feel ...

Abstract: Das Ziel des Datensatzes ist das Training und die Validierung von Modellen zur Vorhersage von Zeitreihen für Fräsprozesse. Dazu wurden an einer DMC 60H Prozesse mit einer Abtastrate von 500 Hz durch eine Siemens Industrial Edge aufgenommen. Die Maschine wurde steuerungstechnisch aufgerüstet. Es wurden Prozesse für das Modelltraining und die Validierung aufgenommen, welche sowohl für die Bearbeitung von Stahl sowie von Aluminium verwendet wurden. Es wurden mehrere Aufnahmen mit und ohne Werkstück (Aircut) erstellt, um möglichst viele Fälle abdecken zu können. Es handelt sich um die gleiche Versuchsreihe wie in "Training and validation dataset of milling processes for time series prediction" mit der DOI 10.5445/IR/1000157789 und hat zum Ziel, eine Untersuchung der Übertragbarkeit von Modellen zwischen verschiedenen Maschinen zu ermöglichen. Abstract: The aim of the dataset is to train and validate models for predicting time series for milling processes. For this purpose, processes were recorded at a sampling rate of 500 Hz by a Siemens Industrial Edge on a DMC 60H. The machine was upgraded in terms of control technology. Processes for model training and validation were recorded, suitable for both steel and aluminum machining. Several recordings were made with and without the workpiece (aircut) in order to cover as many cases as possible. This is the same series of experiments as in "Training and validation dataset of milling processes for time series prediction" with DOI 10.5445/IR/1000157789 and allows an investigation of the transferability of models between different machines. TechnicalRemarks: Documents: -Design of Experiments: Information on the paths such as the technological values of the experiments -Recording information: Information about the recordings with comments -Data: All recorded datasets. The first level contains the folders for training and validation both with and without the workpiece. In the next level, the individual test executions are located. The individual recordings are stored in the form of a JSON file. This consists of a header with all relevant information such as the signal sources. This is followed by the entries of the recorded time series. -NC-Code: NC programs executed on the machine Experimental data: -Machine: Retrofitted DMC 60H -Material: S235JR, 2007 T4 -Tools: -VHM-Fräser HPC, TiSi, ⌀ f8 DC: 5mm -VHM-Fräser HPC, TiSi, ⌀ f8 DC: 10mm -VHM-Fräser HPC, TiSi, ⌀ f8 DC: 20mm -Schaftfräser HSS-Co8, TiAlN, ⌀ k10 DC: 5mm -Schaftfräser HSS-Co8, TiAlN, ⌀ k10 DC: 10mm -Schaftfräser HSS-Co8, TiAlN, ⌀ k10 DC: 5mm -Workpiece blank dimensions: 150x75x50mm License: This work is licensed under a Creative Commons Attribution 4.0 International License. Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).

Given are the training, test and validation performance as measured by Sensitivity (SE) and Positive Predictive Value (PPV). The training and test performances are computed with a 4-fold cross validation on the training set. In the validation step, iSIS was applied to the entire images for taxa detection and the detection results were compared to our gold standard by computing SE and PPV. The performance decreases significantly from the test data to the validation due to an increase in FP. The last row shows SE and PPV results after a careful re-evaluation of the FP (see text for details) yielding our final estimates for iSIS’ SE and PPV. The last column shows the correlation between object counts of the gold standard items and the machine detection result for the full transect.

While the traditional viewpoint in machine learning and statistics assumes training and testing samples come from the same population, practice belies this fiction. One strategy—coming from robust statistics and optimization—is thus to build a model robust to distributional perturbations. In this paper, we take a different approach to describe procedures for robust predictive inference, where a model provides uncertainty estimates on its predictions rather than point predictions. We present a method that produces prediction sets (almost exactly) giving the right coverage level for any test distribution in an f-divergence ball around the training population. The method, based on conformal inference, achieves (nearly) valid coverage in finite samples, under only the condition that the training data be exchangeable. An essential component of our methodology is to estimate the amount of expected future data shift and build robustness to it; we develop estimators and prove their consistency for protection and validity of uncertainty estimates under shifts. By experimenting on several large-scale benchmark datasets, including Recht et al.’s CIFAR-v4 and ImageNet-V2 datasets, we provide complementary empirical results that highlight the importance of robust predictive validity.

Utilize our machine learning datasets to develop and validate your models. Our datasets are designed to support a variety of machine learning applications, from image recognition to natural language processing and recommendation systems. You can access a comprehensive dataset or tailor a subset to fit your specific requirements, using data from a combination of various sources and websites, including custom ones. Popular use cases include model training and validation, where the dataset can be used to ensure robust performance across different applications. Additionally, the dataset helps in algorithm benchmarking by providing extensive data to test and compare various machine learning algorithms, identifying the most effective ones for tasks such as fraud detection, sentiment analysis, and predictive maintenance. Furthermore, it supports feature engineering by allowing you to uncover significant data attributes, enhancing the predictive accuracy of your machine learning models for applications like customer segmentation, personalized marketing, and financial forecasting.

This is an open source - publicly available dataset which can be found at https://shahariarrabby.github.io/ekush/ . We split the dataset into three sets - train, validation, and test. For our experiments, we created two other versions of the dataset. We have applied 10-fold cross validation on the train set and created ten folds. We also created ten bags of datasets using bootstrap aggregating method on the train and validation sets. Lastly, we created another dataset using pre-trained ResNet50 model as feature extractor. On the features extracted by ResNet50 we have applied PCA and created a tabilar dataset containing 80 features. pca_features.csv is the train set and pca_test_features.csv is the test set. Fold.tar.gz contains the ten folds of images described above. Those folds are also been compressed. Similarly, Bagging.tar.gz contains the ten compressed bags of images. The original train, validation, and test sets are in Train.tar.gz, Validation.tar.gz, and Test.tar.gz, respectively. The compression has been performed for speeding up the upload and download purpose and mostly for the sake of convenience. If anyone has any question about how the datasets are organized please feel free to ask me at shiblygnr@gmail.com .I will get back to you in earliest time possible.

Description: Downsized (256x256) camera trap images used for the analyses in "Can CNN-based species classification generalise across variation in habitat within a camera trap survey?", and the dataset composition for each analysis. Note that images tagged as 'human' have been removed from this dataset. Full-size images for the BorneoCam dataset will be made available at LILA.science. The full SAFE camera trap dataset metadata is available at DOI: 10.5281/zenodo.6627707. Project: This dataset was collected as part of the following SAFE research project: Machine learning and image recognition to monitor spatio-temporal changes in the behaviour and dynamics of species interactions Funding: These data were collected as part of research funded by:

NERC (NERC QMEE CDT Studentship, NE/P012345/1, http://gotw.nerc.ac.uk/list_full.asp?pcode=NE%2FP012345%2F1&cookieConsent=A) This dataset is released under the CC-BY 4.0 licence, requiring that you cite the dataset in any outputs, but has the additional condition that you acknowledge the contribution of these funders in any outputs.

XML metadata: GEMINI compliant metadata for this dataset is available here Files: This dataset consists of 3 files: CT_image_data_info2.xlsx, DN_256x256_image_files.zip, DN_generalisability_code.zip CT_image_data_info2.xlsx This file contains dataset metadata and 1 data tables:

Dataset Images (described in worksheet Dataset_images) Description: This worksheet details the composition of each dataset used in the analyses Number of fields: 69 Number of data rows: 270287 Fields:

filename: Root ID (Field type: id) camera_trap_site: Site ID for the camera trap location (Field type: location) taxon: Taxon recorded by camera trap (Field type: taxa) dist_level: Level of disturbance at site (Field type: ordered categorical) baseline: Label as to whether image is included in the baseline training, validation (val) or test set, or not included (NA) (Field type: categorical) increased_cap: Label as to whether image is included in the 'increased cap' training, validation (val) or test set, or not included (NA) (Field type: categorical) dist_individ_event_level: Label as to whether image is included in the 'individual disturbance level datasets split at event level' training, validation (val) or test set, or not included (NA) (Field type: categorical) dist_combined_event_level_1: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance level 1' training or test set, or not included (NA) (Field type: categorical) dist_combined_event_level_2: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance level 2' training or test set, or not included (NA) (Field type: categorical) dist_combined_event_level_3: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance level 3' training or test set, or not included (NA) (Field type: categorical) dist_combined_event_level_4: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance level 4' training or test set, or not included (NA) (Field type: categorical) dist_combined_event_level_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance level 5' training or test set, or not included (NA) (Field type: categorical) dist_combined_event_level_pair_1_2: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1 and 2 (pair)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_pair_1_3: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1 and 3 (pair)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_pair_1_4: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1 and 4 (pair)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_pair_1_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1 and 5 (pair)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_pair_2_3: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 2 and 3 (pair)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_pair_2_4: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 2 and 4 (pair)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_pair_2_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 2 and 5 (pair)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_pair_3_4: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 3 and 4 (pair)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_pair_3_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 3 and 5 (pair)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_pair_4_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 4 and 5 (pair)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_triple_1_2_3: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 2 and 3 (triple)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_triple_1_2_4: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 2 and 4 (triple)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_triple_1_2_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 2 and 5 (triple)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_triple_1_3_4: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 3 and 4 (triple)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_triple_1_3_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 3 and 5 (triple)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_triple_1_4_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 4 and 5 (triple)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_triple_2_3_4: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 2, 3 and 4 (triple)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_triple_2_3_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 2, 3 and 5 (triple)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_triple_2_4_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 2, 4 and 5 (triple)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_triple_3_4_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 3, 4 and 5 (triple)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_quad_1_2_3_4: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 2, 3 and 4 (quad)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_quad_1_2_3_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 2, 3 and 5 (quad)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_quad_1_2_4_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 2, 4 and 5 (quad)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_quad_1_3_4_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 3, 4 and 5 (quad)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_quad_2_3_4_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 2, 3, 4 and 5 (quad)' training set, or not included (NA) (Field type: categorical) dist_combined_event_level_all_1_2_3_4_5: Label as to whether image is included in the 'disturbance level combination analysis split at event level: disturbance levels 1, 2, 3, 4 and 5 (all)' training set, or not included (NA) (Field type: categorical) dist_camera_level_individ_1: Label as to whether image is included in the 'disturbance level combination analysis split at camera level: disturbance