Upload folder using huggingface_hub (#34)

- c57431d3f727598a7a502424e6013b77062f8013df0be3a00a449a2568a34bde (a5c9c11a371a16f561bf0771a583a7eed6e06bf0)

.gitattributes

@@ -0,0 +1,6 @@
+data/datasets/local/spotify/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
+data/datasets/local/spotify/text/lang_detection/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
+data/datasets/local/spotify/text/sbert/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
+data/datasets/local/spotify/text/sbert/embedding/local/outerspace/v34/data-00000-of-00001.parquet filter=lfs diff=lfs merge=lfs -text
+data/datasets/local/spotify/text/sbert/embeddings-00000-of-00001.keys.pkl filter=lfs diff=lfs merge=lfs -text
+data/datasets/local/spotify/text/sbert/embeddings-00000-of-00001.npy filter=lfs diff=lfs merge=lfs -text

data/datasets/local/spotify/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32224657332b09187a737c73ab634f9d14c9ba9a240bd105f1b9819cde2afcef
+size 37128682

data/datasets/local/spotify/manifest.json

@@ -0,0 +1,27 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "data_schema": {
+    "fields": {
+      "artist": {
+        "dtype": "string"
+      },
+      "song": {
+        "dtype": "string"
+      },
+      "link": {
+        "dtype": "string"
+      },
+      "text": {
+        "dtype": "string"
+      },
+      "__line_number__": {
+        "dtype": "int64"
+      },
+      "__rowid__": {
+        "dtype": "string"
+      }
+    }
+  }
+}

data/datasets/local/spotify/settings.json

@@ -0,0 +1 @@
+{"ui": {"media_paths": [["text"]]}}

data/datasets/local/spotify/text/lang_detection/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1555427c8dc3b2f1e9310f5e71b46297e607f710365e107c73c894d5a8e1b0
+size 2033407

data/datasets/local/spotify/text/lang_detection/signal_manifest.json

@@ -0,0 +1,36 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "lang_detection(text)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "text": {
+        "fields": {
+          "lang_detection": {
+            "repeated_field": {
+              "fields": {
+                "lang_code": {
+                  "dtype": "string"
+                }
+              },
+              "dtype": "string_span"
+            },
+            "signal": {
+              "signal_name": "lang_detection"
+            }
+          }
+        }
+      }
+    }
+  },
+  "signal": {
+    "signal_name": "lang_detection"
+  },
+  "enriched_path": [
+    "text"
+  ]
+}

data/datasets/local/spotify/text/sbert/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9796beb630cc3503f3c2ac9db8f71e4c1604570836d78bbf364e801cd427c39e
+size 2709987

data/datasets/local/spotify/text/sbert/embedding/local/outerspace/v34/data-00000-of-00001.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ba0fe68cc02849b0a20b7f72047c8e9cb8e5ef5b57b0cd642fa0b0be8a6e06
+size 3340135

data/datasets/local/spotify/text/sbert/embedding/local/outerspace/v34/signal_manifest.json

@@ -0,0 +1,64 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "local/outerspace/v34(text.sbert.*.embedding)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "text": {
+        "fields": {
+          "sbert": {
+            "repeated_field": {
+              "fields": {
+                "embedding": {
+                  "fields": {
+                    "local/outerspace/v34": {
+                      "dtype": "float32",
+                      "signal": {
+                        "signal_name": "concept_score",
+                        "embedding": "sbert",
+                        "namespace": "local",
+                        "concept_name": "outerspace",
+                        "draft": "main",
+                        "num_negative_examples": 100
+                      },
+                      "bins": [
+                        [
+                          "Not in concept",
+                          null,
+                          0.5
+                        ],
+                        [
+                          "In concept",
+                          0.5,
+                          null
+                        ]
+                      ]
+                    }
+                  }
+                }
+              }
+            }
+          }
+        }
+      }
+    }
+  },
+  "signal": {
+    "signal_name": "concept_score",
+    "embedding": "sbert",
+    "namespace": "local",
+    "concept_name": "outerspace",
+    "draft": "main",
+    "num_negative_examples": 100
+  },
+  "enriched_path": [
+    "text",
+    "sbert",
+    "*",
+    "embedding"
+  ]
+}

data/datasets/local/spotify/text/sbert/embeddings-00000-of-00001.keys.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5df43291782b8c731d4ce56537946654c642a01dc9a4e37de394836362f6b45
+size 3727400

data/datasets/local/spotify/text/sbert/embeddings-00000-of-00001.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e10c23d7229541e1f60b791a659d13673b10a03649abf0ae092e0e18c5aee3
+size 170446976

data/datasets/local/spotify/text/sbert/signal_manifest.json

@@ -0,0 +1,37 @@
+{
+  "files": [
+    "data-00000-of-00001.parquet"
+  ],
+  "parquet_id": "sbert(text)",
+  "data_schema": {
+    "fields": {
+      "__rowid__": {
+        "dtype": "string"
+      },
+      "text": {
+        "fields": {
+          "sbert": {
+            "repeated_field": {
+              "fields": {
+                "embedding": {
+                  "dtype": "embedding"
+                }
+              },
+              "dtype": "string_span"
+            },
+            "signal": {
+              "signal_name": "sbert"
+            }
+          }
+        }
+      }
+    }
+  },
+  "signal": {
+    "signal_name": "sbert"
+  },
+  "enriched_path": [
+    "text"
+  ],
+  "embedding_filename_prefix": "embeddings-00000-of-00001"
+}