Cluster analysis is one of the multivariate statistical analysis methods that helps to separate units and variables into similar sub-clusters  whose groups are not known precisely. It is frequently used in chemometric studies. The GC/MS data of the samples were used for clustering of the stinging nettle samples. GC/MS spectroscopy is a fast and fast spectroscopic method that is frequently used in basic and health sciences, for the determination of elements in multicomponent mixtures, for advanced molecular structure determination, and for qualitative and quantitative studies. The basis of this method is based on the determination of the elements depending on the masses of the substances in the mass spectrometer by ionizing the substances in the mixture after they are separated from each other in gas chromatography. It is also a method used to extract the maximum number of analytical information from the spectrum without preprocessing the data. First of all, the number of clusters was determined by applying the Elbow method to the spectrum data obtained from the samples. As a result of this process, it was seen that the data were divided into 3 clusters. After the data were reduced to 2 dimensions with principal component analysis (PCA), clusters of samples were determined by applying Hierarchical Clustering (HCA). 20% of the data whose clusters were determined were randomly selected to be used as test data. The rest of the data was used to train deep learning. Test data was checked after training and its accuracy was found to be 100%. The proposed method gives reliable results in clustering of GC/MS samples with its fast, cheap and no pre-processing advantages.