Machine learning approaches has the advantage that in most of machine leaning algorithms data transformation is unnecessary, can handle missing predictor variables, success of prediction is not dependent on data meeting normality conditions or covariance homogeneity, variable selection is intrinsic to the methodology and provides good accuracy over the traditional methods. The decision tree is one of such machine learning algorithms which is capable of handling both complete and incomplete data, so it can be applied in the field of agriculture where such data occurs frequently. The algorithms which were considered for this study includes ID3 (Iterative Dichotomizer 3), Classification and Regression Tree (CART) and C4.5. This paper provides a detailed approach on the development of decision tree using its various algorithms. It is anticipated that this study will be a layman guide to all agriculture researchers towards enhancing awareness of the potential advantages of using decision tree in agriculture, and contributing to its wide applicability in the agriculture data. The secondary data of cotton genotypes was used for classifying the genotypes into two classes, and hold out method was used for cross validation for checking the performance of the algorithms.

Mixed data is a combination of continuous and categorical variables and occurs frequently in fields such as agriculture, remote sensing, biology, medical science, marketing, etc., but only limited work has been done with this type of data. In this study, data on continuous and categorical characters of 452 genotypes of cotton (Gossypium hirsutum) were obtained from an experiment conducted by the Central Institute of Cotton Research (CICR), Sirsa, Haryana (India) during the Kharif season of the year 2018–2019. The machine learning (ML) classifiers/models, namely k-nearest neighbor (KNN), Classification and Regression Tree (CART), C4.5, Naïve Bayes, random forest (RF), bagging, and boosting were considered for cotton genotypes classification. The performance of these ML classifiers was compared to each other along with the linear discriminant analysis (LDA) and logistic regression. The holdout method was used for cross-validation with an 80:20 ratio of training and testing data. The results of the appraisal based on hold-out cross-validation showed that the RF and AdaBoost performed very well, having only two misclassifications with the same accuracy of 97.26% and the error rate of 2.74%. The LDA classifier performed the worst in terms of accuracy, with nine misclassifications. The other performance measures, namely sensitivity, specificity, precision, F1 score, and G-mean, were all together used to find out the best ML classifier among all those considered. Moreover, the RF and AdaBoost algorithms had the highest value of all the performance measures, with 96.97% sensitivity and 97.50% specificity. Thus, these models were found to be the best in classifying the low- and high-yielding cotton genotypes.

Machine learning has emerged together with big data technologies and high performance computing to create new opportunities to unravel, quantify and understand data intensive processes in agricultural environments. The Naive Bayes is one of such machine learning algorithms which is capable of handling both complete and incomplete data, so it can be applied in the field of agriculture where such data occurs frequently. This paper provides a detailed approach on the development of Naive Bayes classification algorithm to classify cotton genotypes. The secondary data of cotton genotypes was used for classifying the genotypes into two classes, and hold out method was used for cross validation for checking the performance of the algorithm.