Step 6 data and model version control

.dvc/.gitignore

@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache

.dvc/config

@@ -0,0 +1,8 @@
+[core]
+    remote = myremote-amazon
+['remote "myremote"']
+    url = /tmp/dvc
+['remote "localremote"']
+    url = ../../../localremote
+['remote "myremote-amazon"']
+    url = ../arn:aws:s3:::bee-ml-dataset-jan-24

.dvc/plots/confusion.json

@@ -0,0 +1,107 @@
+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v5.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "facet": {
+        "field": "rev",
+        "type": "nominal"
+    },
+    "spec": {
+        "transform": [
+            {
+                "aggregate": [
+                    {
+                        "op": "count",
+                        "as": "xy_count"
+                    }
+                ],
+                "groupby": [
+                    "<DVC_METRIC_Y>",
+                    "<DVC_METRIC_X>"
+                ]
+            },
+            {
+                "impute": "xy_count",
+                "groupby": [
+                    "rev",
+                    "<DVC_METRIC_Y>"
+                ],
+                "key": "<DVC_METRIC_X>",
+                "value": 0
+            },
+            {
+                "impute": "xy_count",
+                "groupby": [
+                    "rev",
+                    "<DVC_METRIC_X>"
+                ],
+                "key": "<DVC_METRIC_Y>",
+                "value": 0
+            },
+            {
+                "joinaggregate": [
+                    {
+                        "op": "max",
+                        "field": "xy_count",
+                        "as": "max_count"
+                    }
+                ],
+                "groupby": []
+            },
+            {
+                "calculate": "datum.xy_count / datum.max_count",
+                "as": "percent_of_max"
+            }
+        ],
+        "encoding": {
+            "x": {
+                "field": "<DVC_METRIC_X>",
+                "type": "nominal",
+                "sort": "ascending",
+                "title": "<DVC_METRIC_X_LABEL>"
+            },
+            "y": {
+                "field": "<DVC_METRIC_Y>",
+                "type": "nominal",
+                "sort": "ascending",
+                "title": "<DVC_METRIC_Y_LABEL>"
+            }
+        },
+        "layer": [
+            {
+                "mark": "rect",
+                "width": 300,
+                "height": 300,
+                "encoding": {
+                    "color": {
+                        "field": "xy_count",
+                        "type": "quantitative",
+                        "title": "",
+                        "scale": {
+                            "domainMin": 0,
+                            "nice": true
+                        }
+                    }
+                }
+            },
+            {
+                "mark": "text",
+                "encoding": {
+                    "text": {
+                        "field": "xy_count",
+                        "type": "quantitative"
+                    },
+                    "color": {
+                        "condition": {
+                            "test": "datum.percent_of_max > 0.5",
+                            "value": "white"
+                        },
+                        "value": "black"
+                    }
+                }
+            }
+        ]
+    }
+}

.dvc/plots/confusion_normalized.json

@@ -0,0 +1,112 @@
+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v5.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "facet": {
+        "field": "rev",
+        "type": "nominal"
+    },
+    "spec": {
+        "transform": [
+            {
+                "aggregate": [
+                    {
+                        "op": "count",
+                        "as": "xy_count"
+                    }
+                ],
+                "groupby": [
+                    "<DVC_METRIC_Y>",
+                    "<DVC_METRIC_X>"
+                ]
+            },
+            {
+                "impute": "xy_count",
+                "groupby": [
+                    "rev",
+                    "<DVC_METRIC_Y>"
+                ],
+                "key": "<DVC_METRIC_X>",
+                "value": 0
+            },
+            {
+                "impute": "xy_count",
+                "groupby": [
+                    "rev",
+                    "<DVC_METRIC_X>"
+                ],
+                "key": "<DVC_METRIC_Y>",
+                "value": 0
+            },
+            {
+                "joinaggregate": [
+                    {
+                        "op": "sum",
+                        "field": "xy_count",
+                        "as": "sum_y"
+                    }
+                ],
+                "groupby": [
+                    "<DVC_METRIC_Y>"
+                ]
+            },
+            {
+                "calculate": "datum.xy_count / datum.sum_y",
+                "as": "percent_of_y"
+            }
+        ],
+        "encoding": {
+            "x": {
+                "field": "<DVC_METRIC_X>",
+                "type": "nominal",
+                "sort": "ascending",
+                "title": "<DVC_METRIC_X_LABEL>"
+            },
+            "y": {
+                "field": "<DVC_METRIC_Y>",
+                "type": "nominal",
+                "sort": "ascending",
+                "title": "<DVC_METRIC_Y_LABEL>"
+            }
+        },
+        "layer": [
+            {
+                "mark": "rect",
+                "width": 300,
+                "height": 300,
+                "encoding": {
+                    "color": {
+                        "field": "percent_of_y",
+                        "type": "quantitative",
+                        "title": "",
+                        "scale": {
+                            "domain": [
+                                0,
+                                1
+                            ]
+                        }
+                    }
+                }
+            },
+            {
+                "mark": "text",
+                "encoding": {
+                    "text": {
+                        "field": "percent_of_y",
+                        "type": "quantitative",
+                        "format": ".2f"
+                    },
+                    "color": {
+                        "condition": {
+                            "test": "datum.percent_of_y > 0.5",
+                            "value": "white"
+                        },
+                        "value": "black"
+                    }
+                }
+            }
+        ]
+    }
+}

.dvc/plots/linear.json

@@ -0,0 +1,116 @@
+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v5.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "width": 300,
+    "height": 300,
+    "layer": [
+        {
+            "encoding": {
+                "x": {
+                    "field": "<DVC_METRIC_X>",
+                    "type": "quantitative",
+                    "title": "<DVC_METRIC_X_LABEL>"
+                },
+                "y": {
+                    "field": "<DVC_METRIC_Y>",
+                    "type": "quantitative",
+                    "title": "<DVC_METRIC_Y_LABEL>",
+                    "scale": {
+                        "zero": false
+                    }
+                },
+                "color": {
+                    "field": "rev",
+                    "type": "nominal"
+                }
+            },
+            "layer": [
+                {
+                    "mark": "line"
+                },
+                {
+                    "selection": {
+                        "label": {
+                            "type": "single",
+                            "nearest": true,
+                            "on": "mouseover",
+                            "encodings": [
+                                "x"
+                            ],
+                            "empty": "none",
+                            "clear": "mouseout"
+                        }
+                    },
+                    "mark": "point",
+                    "encoding": {
+                        "opacity": {
+                            "condition": {
+                                "selection": "label",
+                                "value": 1
+                            },
+                            "value": 0
+                        }
+                    }
+                }
+            ]
+        },
+        {
+            "transform": [
+                {
+                    "filter": {
+                        "selection": "label"
+                    }
+                }
+            ],
+            "layer": [
+                {
+                    "mark": {
+                        "type": "rule",
+                        "color": "gray"
+                    },
+                    "encoding": {
+                        "x": {
+                            "field": "<DVC_METRIC_X>",
+                            "type": "quantitative"
+                        }
+                    }
+                },
+                {
+                    "encoding": {
+                        "text": {
+                            "type": "quantitative",
+                            "field": "<DVC_METRIC_Y>"
+                        },
+                        "x": {
+                            "field": "<DVC_METRIC_X>",
+                            "type": "quantitative"
+                        },
+                        "y": {
+                            "field": "<DVC_METRIC_Y>",
+                            "type": "quantitative"
+                        }
+                    },
+                    "layer": [
+                        {
+                            "mark": {
+                                "type": "text",
+                                "align": "left",
+                                "dx": 5,
+                                "dy": -5
+                            },
+                            "encoding": {
+                                "color": {
+                                    "type": "nominal",
+                                    "field": "rev"
+                                }
+                            }
+                        }
+                    ]
+                }
+            ]
+        }
+    ]
+}