From 14eb7182744f48c68c222a2b52229f31fd818970 Mon Sep 17 00:00:00 2001
From: Wojciech Jarmosz <wojciech@jarmosz.com>
Date: Sat, 12 Jun 2021 20:35:33 +0200
Subject: [PATCH] Add dvc support

---
 .dvc/.gitignore                      |   3 +
 .dvc/config                          |   0
 .dvc/plots/confusion.json            | 107 ++++++++++++++++++++++++
 .dvc/plots/confusion_normalized.json | 112 ++++++++++++++++++++++++++
 .dvc/plots/default.json              |  31 +++++++
 .dvc/plots/linear.json               | 116 +++++++++++++++++++++++++++
 .dvc/plots/scatter.json              | 104 ++++++++++++++++++++++++
 .dvc/plots/smooth.json               |  39 +++++++++
 .dvcignore                           |   3 +
 9 files changed, 515 insertions(+)
 create mode 100644 .dvc/.gitignore
 create mode 100644 .dvc/config
 create mode 100644 .dvc/plots/confusion.json
 create mode 100644 .dvc/plots/confusion_normalized.json
 create mode 100644 .dvc/plots/default.json
 create mode 100644 .dvc/plots/linear.json
 create mode 100644 .dvc/plots/scatter.json
 create mode 100644 .dvc/plots/smooth.json
 create mode 100644 .dvcignore

diff --git a/.dvc/.gitignore b/.dvc/.gitignore
new file mode 100644
index 0000000..528f30c
--- /dev/null
+++ b/.dvc/.gitignore
@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache
diff --git a/.dvc/config b/.dvc/config
new file mode 100644
index 0000000..e69de29
diff --git a/.dvc/plots/confusion.json b/.dvc/plots/confusion.json
new file mode 100644
index 0000000..af1b48d
--- /dev/null
+++ b/.dvc/plots/confusion.json
@@ -0,0 +1,107 @@
+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v4.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"
+                    }
+                }
+            }
+        ]
+    }
+}
diff --git a/.dvc/plots/confusion_normalized.json b/.dvc/plots/confusion_normalized.json
new file mode 100644
index 0000000..1d38849
--- /dev/null
+++ b/.dvc/plots/confusion_normalized.json
@@ -0,0 +1,112 @@
+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v4.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"
+                    }
+                }
+            }
+        ]
+    }
+}
diff --git a/.dvc/plots/default.json b/.dvc/plots/default.json
new file mode 100644
index 0000000..9cf71ce
--- /dev/null
+++ b/.dvc/plots/default.json
@@ -0,0 +1,31 @@
+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v4.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "width": 300,
+    "height": 300,
+    "mark": {
+        "type": "line"
+    },
+    "encoding": {
+        "x": {
+            "field": "<DVC_METRIC_X>",
+            "type": "quantitative",
+            "title": "<DVC_METRIC_X_LABEL>"
+        },
+        "y": {
+            "field": "<DVC_METRIC_Y>",
+            "type": "quantitative",
+            "title": "<DVC_METRIC_Y_LABEL>",
+            "scale": {
+                "zero": false
+            }
+        },
+        "color": {
+            "field": "rev",
+            "type": "nominal"
+        }
+    }
+}
diff --git a/.dvc/plots/linear.json b/.dvc/plots/linear.json
new file mode 100644
index 0000000..65549f9
--- /dev/null
+++ b/.dvc/plots/linear.json
@@ -0,0 +1,116 @@
+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v4.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"
+                                }
+                            }
+                        }
+                    ]
+                }
+            ]
+        }
+    ]
+}
diff --git a/.dvc/plots/scatter.json b/.dvc/plots/scatter.json
new file mode 100644
index 0000000..9af9304
--- /dev/null
+++ b/.dvc/plots/scatter.json
@@ -0,0 +1,104 @@
+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v4.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": "point"
+                },
+                {
+                    "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": [
+                {
+                    "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"
+                                }
+                            }
+                        }
+                    ]
+                }
+            ]
+        }
+    ]
+}
diff --git a/.dvc/plots/smooth.json b/.dvc/plots/smooth.json
new file mode 100644
index 0000000..d497ce7
--- /dev/null
+++ b/.dvc/plots/smooth.json
@@ -0,0 +1,39 @@
+{
+    "$schema": "https://vega.github.io/schema/vega-lite/v4.json",
+    "data": {
+        "values": "<DVC_METRIC_DATA>"
+    },
+    "title": "<DVC_METRIC_TITLE>",
+    "mark": {
+        "type": "line"
+    },
+    "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"
+        }
+    },
+    "transform": [
+        {
+            "loess": "<DVC_METRIC_Y>",
+            "on": "<DVC_METRIC_X>",
+            "groupby": [
+                "rev"
+            ],
+            "bandwidth": 0.3
+        }
+    ]
+}
diff --git a/.dvcignore b/.dvcignore
new file mode 100644
index 0000000..5197305
--- /dev/null
+++ b/.dvcignore
@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore