{ "__type": "IngestedDoc", "__tag": 4010, "_content": { "Notes": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "This function is similar to the MATLAB function " }, { "__type": "InlineCode", "__tag": 4051, "value": "clusterdata" }, { "__type": "Text", "__tag": 4046, "value": "." } ] }, { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Strong", "__tag": 4048, "children": [ { "__type": "Text", "__tag": 4046, "value": "Array API Standard Support" } ] } ] }, { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "CrossRef", "__tag": 4002, "value": "fclusterdata", "reference": { "__type": "RefInfo", "__tag": 4000, "module": null, "version": null, "kind": "local", "path": "fclusterdata" }, "kind": "local" }, { "__type": "Text", "__tag": 4046, "value": " has experimental support for Python Array API Standard compatible backends in addition to NumPy. Please consider testing these features by setting an environment variable " }, { "__type": "InlineCode", "__tag": 4051, "value": "SCIPY_ARRAY_API=1" }, { "__type": "Text", "__tag": 4046, "value": " and providing CuPy, PyTorch, JAX, or Dask arrays as array arguments. The following combinations of backend and device (or other capability) are supported." } ] }, { "__type": "Code", "__tag": 4050, "value": "==================== ==================== ====================\nLibrary CPU GPU\n==================== ==================== ====================\nNumPy ✅ n/a \nCuPy n/a ⛔ \nPyTorch ✅ ⛔ \nJAX ⚠️ no JIT ⛔ \nDask ⚠️ computes graph n/a \n==================== ==================== ====================", "execution_status": null }, { "__type": "Blockquote", "__tag": 4059, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "See " }, { "__type": "InlineRole", "__tag": 4003, "value": "dev-arrayapi", "domain": null, "role": "ref", "inventory": null }, { "__type": "Text", "__tag": 4046, "value": " for more information." } ] } ] } ], "title": [], "level": 0, "target": null }, "Warns": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Raises": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Yields": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Methods": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Returns": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Parameters", "__tag": 4026, "children": [ { "__type": "DocParam", "__tag": 4016, "name": "fclusterdata", "annotation": "ndarray", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "A vector of length n. T[i] is the flat cluster number to which original observation i belongs." } ] } ] } ] } ], "title": [], "level": 0, "target": null }, "Summary": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "Cluster observation data using a given metric." } ] } ], "title": [], "level": 0, "target": null }, "Receives": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Warnings": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Attributes": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null }, "Parameters": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Parameters", "__tag": 4026, "children": [ { "__type": "DocParam", "__tag": 4016, "name": "X", "annotation": "(N, M) ndarray", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "N by M data matrix with N observations in M dimensions." } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "t", "annotation": "scalar", "desc": [ { "__type": "DefList", "__tag": 4033, "children": [ { "__type": "DefListItem", "__tag": 4037, "dt": { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "For criteria 'inconsistent', 'distance' or 'monocrit'," } ] }, "dd": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "this is the threshold to apply when forming flat clusters." } ] } ] }, { "__type": "DefListItem", "__tag": 4037, "dt": { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "For 'maxclust' or 'maxclust_monocrit' criteria," } ] }, "dd": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "this would be max number of clusters requested." } ] } ] } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "criterion", "annotation": "str, optional", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "Specifies the criterion for forming flat clusters. Valid values are 'inconsistent' (default), 'distance', or 'maxclust' cluster formation algorithms. See " }, { "__type": "CrossRef", "__tag": 4002, "value": "fcluster", "reference": { "__type": "LocalRef", "__tag": 4022, "kind": "module", "path": "scipy.cluster.hierarchy:fcluster" }, "kind": "module" }, { "__type": "Text", "__tag": 4046, "value": " for descriptions." } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "metric", "annotation": "str or function, optional", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "The distance metric for calculating pairwise distances. See " }, { "__type": "InlineCode", "__tag": 4051, "value": "distance.pdist" }, { "__type": "Text", "__tag": 4046, "value": " for descriptions and linkage to verify compatibility with the linkage method." } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "depth", "annotation": "int, optional", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "The maximum depth for the inconsistency calculation. See " }, { "__type": "InlineRole", "__tag": 4003, "value": "inconsistent", "domain": null, "role": null, "inventory": null }, { "__type": "Text", "__tag": 4046, "value": " for more information." } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "method", "annotation": "str, optional", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "The linkage method to use (single, complete, average, weighted, median centroid, ward). See " }, { "__type": "InlineRole", "__tag": 4003, "value": "linkage", "domain": null, "role": null, "inventory": null }, { "__type": "Text", "__tag": 4046, "value": " for more information. Default is \"single\"." } ] } ] }, { "__type": "DocParam", "__tag": 4016, "name": "R", "annotation": "ndarray, optional", "desc": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "The inconsistency matrix. It will be computed if necessary if it is not passed." } ] } ] } ] } ], "title": [], "level": 0, "target": null }, "Extended Summary": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "Clusters the original observations in the n-by-m data matrix X (n observations in m dimensions), using the euclidean distance metric to calculate distances between original observations, performs hierarchical clustering using the single linkage algorithm, and forms flat clusters using the inconsistency method with " }, { "__type": "ParamRef", "__tag": 4071, "name": "t" }, { "__type": "Text", "__tag": 4046, "value": " as the cut-off threshold." } ] }, { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "A 1-D array " }, { "__type": "InlineCode", "__tag": 4051, "value": "T" }, { "__type": "Text", "__tag": 4046, "value": " of length " }, { "__type": "InlineCode", "__tag": 4051, "value": "n" }, { "__type": "Text", "__tag": 4046, "value": " is returned. " }, { "__type": "InlineCode", "__tag": 4051, "value": "T[i]" }, { "__type": "Text", "__tag": 4046, "value": " is the index of the flat cluster to which the original observation " }, { "__type": "InlineCode", "__tag": 4051, "value": "i" }, { "__type": "Text", "__tag": 4046, "value": " belongs." } ] } ], "title": [], "level": 0, "target": null }, "Other Parameters": { "__type": "Section", "__tag": 4015, "children": [], "title": [], "level": 0, "target": null } }, "_ordered_sections": [ "Summary", "Extended Summary", "Parameters", "Attributes", "Methods", "Returns", "Yields", "Receives", "Other Parameters", "Raises", "Warns", "Warnings", "Notes" ], "item_file": "/scipy/cluster/hierarchy.py", "item_line": 2703, "item_type": "function", "aliases": [ "scipy.cluster.hierarchy.fclusterdata" ], "example_section_data": { "__type": "Section", "__tag": 4015, "children": [ { "__type": "Code", "__tag": 4050, "value": "from scipy.cluster.hierarchy import fclusterdata\n", "execution_status": "success" }, { "__type": "Text", "__tag": 4046, "value": "\nThis is a convenience method that abstracts all the steps to perform in a\ntypical SciPy's hierarchical clustering workflow.\n\n* Transform the input data into a condensed matrix with\n `scipy.spatial.distance.pdist`.\n\n* Apply a clustering method.\n\n* Obtain flat clusters at a user defined distance threshold ``t`` using\n `scipy.cluster.hierarchy.fcluster`.\n\n" }, { "__type": "Code", "__tag": 4050, "value": "X = [[0, 0], [0, 1], [1, 0],\n [0, 4], [0, 3], [1, 4],\n [4, 0], [3, 0], [4, 1],\n [4, 4], [3, 4], [4, 3]]\n", "execution_status": "success" }, { "__type": "Text", "__tag": 4046, "value": "\n" }, { "__type": "Code", "__tag": 4050, "value": "fclusterdata(X, t=1)\n", "execution_status": "success" }, { "__type": "Text", "__tag": 4046, "value": "\nThe output here (for the dataset ``X``, distance threshold ``t``, and the\ndefault settings) is four clusters with three data points each." } ], "title": [], "level": 0, "target": null }, "see_also": [ { "__type": "SeeAlsoItem", "__tag": 4028, "name": { "__type": "CrossRef", "__tag": 4002, "value": "scipy.spatial.distance.pdist", "reference": { "__type": "LocalRef", "__tag": 4022, "kind": "module", "path": "scipy.spatial.distance:pdist" }, "kind": "module" }, "descriptions": [ { "__type": "Paragraph", "__tag": 4045, "children": [ { "__type": "Text", "__tag": 4046, "value": "pairwise distance metrics" } ] } ], "type": "func" } ], "signature": { "__type": "SignatureNode", "__tag": 4029, "kind": "function", "parameters": [ { "__type": "SigParam", "__tag": 4030, "name": "X", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": { "__type": "Empty", "__tag": 4031 } }, { "__type": "SigParam", "__tag": 4030, "name": "t", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": { "__type": "Empty", "__tag": 4031 } }, { "__type": "SigParam", "__tag": 4030, "name": "criterion", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": "inconsistent" }, { "__type": "SigParam", "__tag": 4030, "name": "metric", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": "euclidean" }, { "__type": "SigParam", "__tag": 4030, "name": "depth", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": "2" }, { "__type": "SigParam", "__tag": 4030, "name": "method", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": "single" }, { "__type": "SigParam", "__tag": 4030, "name": "R", "annotation": { "__type": "Empty", "__tag": 4031 }, "kind": "POSITIONAL_OR_KEYWORD", "default": "None" } ], "return_annotation": { "__type": "Empty", "__tag": 4031 }, "target_name": "fclusterdata" }, "references": null, "qa": "scipy.cluster.hierarchy:fclusterdata", "arbitrary": [], "local_refs": [ "R", "X", "criterion", "depth", "fclusterdata", "method", "metric", "t" ] }