Merge pull request #171 from moj-analytical-services/zoom_chart

Zoomable charts
moj-analytical-services · Jan 31, 2021 · 3811d68 · 3811d68
2 parents 9c116c3 + ae1dbc7
commit 3811d68
Show file tree

Hide file tree

Showing 6 changed files with 68 additions and 8 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 
+## [1.0.1] - 2020-01-31
+
+### Changed
+
+- Added mousewheel zoom to bayes factor chart
+- Added mousewheel zoom to splink score histogram
+- Update estimate comparison chart to use different shapes for different estimates, making it possible to distinguish overlapping symbols
+
+### Fixed
+
+- m and u history charts now display barchart correctly
 
 ## [1.0.0] - 2020-01-20
 ### Added

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "splink"
-version = "1.0.0"
+version = "1.0.1"
 description = "Implementation in Apache Spark of the EM algorithm to estimate parameters of Fellegi-Sunter's canonical model of record linkage."
 authors = ["Robin Linacre <robinlinacre@hotmail.com>", "Sam Lindsay", "Theodore Manassis"]
 license = "MIT"

diff --git a/splink/files/chart_defs/bayes_factor_chart_def.json b/splink/files/chart_defs/bayes_factor_chart_def.json
@@ -21,6 +21,15 @@
         "type": "bar",
         "clip": true
     },
+    "selection": {
+        "selector076": {
+            "type": "interval",
+            "bind": "scales",
+            "encodings": [
+                "x"
+            ]
+        }
+    },
     "encoding": {
         "color": {
             "type": "quantitative",
@@ -116,6 +125,9 @@
             "y": "independent"
         }
     },
-    "title": "Influence of comparison vector values on match probability",
+    "title": {
+        "text": "Influence of comparison vector values on match probability",
+        "subtitle": "Use mousewheeel to zoom"
+    },
     "$schema": "https://vega.github.io/schema/vega-lite/v4.json"
 }
diff --git a/splink/files/chart_defs/compare_estimates.json b/splink/files/chart_defs/compare_estimates.json
@@ -12,8 +12,8 @@
         {
             "mark": {
                 "type": "point",
-                "filled": true,
-                "opacity": 1,
+                "filled": false,
+                "opacity": 0.7,
                 "size": 100
             },
             "encoding": {
@@ -43,6 +43,18 @@
                         "title": null
                     },
                     "field": "level_name"
+                },
+                "shape": {
+                    "type": "nominal",
+                    "field": "estimate_name",
+                    "scale": {
+                        "range": [
+                            "circle",
+                            "square",
+                            "triangle",
+                            "diamond"
+                        ]
+                    }
                 }
             },
             "resolve": {
@@ -70,8 +82,8 @@
         {
             "mark": {
                 "type": "point",
-                "filled": true,
-                "opacity": 1,
+                "filled": false,
+                "opacity": 0.7,
                 "size": 100
             },
             "encoding": {
@@ -101,6 +113,19 @@
                         "title": null
                     },
                     "field": "level_name"
+                },
+                "shape": {
+                    "type": "nominal",
+                    "field": "estimate_name",
+                    "scale": {
+                        "range": [
+                            "circle",
+                            "square",
+                            "triangle",
+                            "diamond",
+                            "cross"
+                        ]
+                    }
                 }
             },
             "resolve": {

diff --git a/splink/files/chart_defs/score_histogram.json b/splink/files/chart_defs/score_histogram.json
@@ -14,7 +14,10 @@
     },
     "height": 200,
     "mark": "bar",
-    "title": "Histogram of splink scores",
+    "title": {
+        "text": "Histogram of splink scores",
+        "subtitle": "Use mousewheeel to zoom"
+    },
     "width": 700,
     "encoding": {
         "tooltip": [
@@ -42,5 +45,14 @@
                 "title": "probability density"
             }
         }
+    },
+    "selection": {
+        "selector076": {
+            "type": "interval",
+            "bind": "scales",
+            "encodings": [
+                "y"
+            ]
+        }
     }
 }
diff --git a/splink/model.py b/splink/model.py
@@ -157,7 +157,7 @@ def m_u_history_as_rows(self):
             new_rows = p.m_u_as_rows()
             for r in new_rows:
                 r["iteration"] = it_num
-                r["final"] = it_num == self.iteration
+                r["final"] = it_num == self.iteration - 1
 
             rows.extend(new_rows)
         return rows