Merge pull request #568 from neuroscout/enh/extract_dict

Extract additional language features
neuroscout · May 15, 2019 · 6394bbc · 6394bbc
2 parents 62c9058 + 7fd8ca2
commit 6394bbc
Show file tree

Hide file tree

Showing 7 changed files with 112 additions and 37 deletions.
diff --git a/neuroscout/config/datasets/ds001338.json b/neuroscout/config/datasets/ds001338.json
@@ -11,12 +11,15 @@
         ],
         "extractors": [
           ["PredefinedDictionaryExtractor", {"variables":
-            {"affect":["V.Mean.Sum", "A.Mean.Sum", "D.Mean.Sum"],
-            "aoa": ["AoA_Kup"],
-            "concreteness": ["Conc.M"]},
-            "missing": "n/a"} ],
-          ["LengthExtractor", {}]
-        ],
+            {"massiveauditorylexicaldecision":
+                ["StressPattern", "NumSylls", "NumPhones", "Duration",
+                  "OrthUP", "PhonND", "OrthND", "POS", "AllPOS", "FreqSUBTLEX",
+                  "FreqCOCA", "FreqCOCAspok", "FreqGoogle", "PhonUP", "StressCat",
+                  "PhonLev", "NumMorphs", "OrthLev"],
+               "calgarysemanticdecision": ["Concrete_rating"]
+              },
+            "missing": "n/a"} ]
+          ],
         "transformations": [
         ],
         "ingest_args": {

diff --git a/neuroscout/config/datasets/ds001545.json b/neuroscout/config/datasets/ds001545.json
@@ -11,14 +11,14 @@
         ],
         "extractors": [
           ["PredefinedDictionaryExtractor", {"variables":
-            {"subtlexusfrequency":["FREQcount", "CDcount", "FREQlow", "Cdlow", "SUBTLWF","Lg10WF", "SUBTLCD", "Lg10CD", "Dom_PoS_SUBTLEX", "Freq_dom_PoS_SUBTLEX", "Percentage_dom_PoS", "All_PoS_SUBTLEX", "All_freqs_SUBTLEX", "Zipf-value"]},
-            "missing": "n/a"} ],
-            ["PredefinedDictionaryExtractor", {"variables":
-              {"affect":["V.Mean.Sum", "A.Mean.Sum", "D.Mean.Sum"],
-              "aoa": ["AoA_Kup"],
-              "concreteness": ["Conc.M"]},
-              "missing": "n/a"} ],
-            ["LengthExtractor", {}]
+            {"massiveauditorylexicaldecision":
+                ["StressPattern", "NumSylls", "NumPhones", "Duration",
+                  "OrthUP", "PhonND", "OrthND", "POS", "AllPOS", "FreqSUBTLEX",
+                  "FreqCOCA", "FreqCOCAspok", "FreqGoogle", "PhonUP", "StressCat",
+                  "PhonLev", "NumMorphs", "OrthLev"],
+               "calgarysemanticdecision": ["Concrete_rating"]
+              },
+            "missing": "n/a"} ]
           ],
         "transformations": [
         ],

diff --git a/neuroscout/config/datasets/forrest.json b/neuroscout/config/datasets/forrest.json
@@ -11,11 +11,14 @@
         ],
         "extractors": [
           ["PredefinedDictionaryExtractor", {"variables":
-            {"affect":["V.Mean.Sum", "A.Mean.Sum", "D.Mean.Sum"],
-            "aoa": ["AoA_Kup"],
-            "concreteness": ["Conc.M"]},
-            "missing": "n/a"} ],
-          ["LengthExtractor", {}]
+            {"massiveauditorylexicaldecision":
+                ["StressPattern", "NumSylls", "NumPhones", "Duration",
+                  "OrthUP", "PhonND", "OrthND", "POS", "AllPOS", "FreqSUBTLEX",
+                  "FreqCOCA", "FreqCOCAspok", "FreqGoogle", "PhonUP", "StressCat",
+                  "PhonLev", "NumMorphs", "OrthLev"],
+               "calgarysemanticdecision": ["Concrete_rating"]
+              },
+            "missing": "n/a"} ]
           ],
         "transformations": [
         ],

diff --git a/neuroscout/config/datasets/hbn.json b/neuroscout/config/datasets/hbn.json
@@ -10,12 +10,15 @@
         ],
         "extractors": [
           ["PredefinedDictionaryExtractor", {"variables":
-            {"affect":["V.Mean.Sum", "A.Mean.Sum", "D.Mean.Sum"],
-            "aoa": ["AoA_Kup"],
-            "concreteness": ["Conc.M"]},
-            "missing": "n/a"} ],
-          ["LengthExtractor", {}]
-        ],
+            {"massiveauditorylexicaldecision":
+                ["StressPattern", "NumSylls", "NumPhones", "Duration",
+                  "OrthUP", "PhonND", "OrthND", "POS", "AllPOS", "FreqSUBTLEX",
+                  "FreqCOCA", "FreqCOCAspok", "FreqGoogle", "PhonUP", "StressCat",
+                  "PhonLev", "NumMorphs", "OrthLev"],
+               "calgarysemanticdecision": ["Concrete_rating"]
+              },
+            "missing": "n/a"} ]
+          ],
         "transformations":[
         ],
         "filters": {

diff --git a/neuroscout/config/datasets/life.json b/neuroscout/config/datasets/life.json
@@ -12,12 +12,15 @@
         ],
         "extractors": [
           ["PredefinedDictionaryExtractor", {"variables":
-            {"affect":["V.Mean.Sum", "A.Mean.Sum", "D.Mean.Sum"],
-            "aoa": ["AoA_Kup"],
-            "concreteness": ["Conc.M"]},
-            "missing": "n/a"} ],
-          ["LengthExtractor", {}]
-        ],
+            {"massiveauditorylexicaldecision":
+                ["StressPattern", "NumSylls", "NumPhones", "Duration",
+                  "OrthUP", "PhonND", "OrthND", "POS", "AllPOS", "FreqSUBTLEX",
+                  "FreqCOCA", "FreqCOCAspok", "FreqGoogle", "PhonUP", "StressCat",
+                  "PhonLev", "NumMorphs", "OrthLev"],
+               "calgarysemanticdecision": ["Concrete_rating"]
+              },
+            "missing": "n/a"} ]
+          ],
         "transformations":[
         ]
       }

diff --git a/neuroscout/config/datasets/raiders.json b/neuroscout/config/datasets/raiders.json
@@ -11,12 +11,15 @@
         ],
         "extractors": [
           ["PredefinedDictionaryExtractor", {"variables":
-            {"affect":["V.Mean.Sum", "A.Mean.Sum", "D.Mean.Sum"],
-            "aoa": ["AoA_Kup"],
-            "concreteness": ["Conc.M"]},
-            "missing": "n/a"} ],
-          ["LengthExtractor", {}]
-        ],
+            {"massiveauditorylexicaldecision":
+                ["StressPattern", "NumSylls", "NumPhones", "Duration",
+                  "OrthUP", "PhonND", "OrthND", "POS", "AllPOS", "FreqSUBTLEX",
+                  "FreqCOCA", "FreqCOCAspok", "FreqGoogle", "PhonUP", "StressCat",
+                  "PhonLev", "NumMorphs", "OrthLev"],
+               "calgarysemanticdecision": ["Concrete_rating"]
+              },
+            "missing": "n/a"} ]
+          ],
         "transformations":[
         ]
       }

diff --git a/neuroscout/config/feature_schema.json b/neuroscout/config/feature_schema.json
@@ -333,6 +333,66 @@
         },
         "aoa.AoA_Kup": {
           "description": "Age of aquisition of spoken words."
+        },
+        "massiveauditorylexicaldecision_IsWord": {
+          "description": "Whether the item is a word or pseudo-word."
+        },
+        "massiveauditorylexicaldecision_StressPattern": {
+          "description": "The stress pattern of the word."
+        },
+        "massiveauditorylexicaldecision_NumSylls": {
+          "description": "The number of syllables in the item."
+        },
+        "massiveauditorylexicaldecision_NumPhones": {
+          "description": "The number of phones in the item."
+        },
+        "massiveauditorylexicaldecision_Duration": {
+          "description": "The duration of the item in milliseconds."
+        },
+        "massiveauditorylexicaldecision_OrthUP": {
+          "description": "The letter index of the orthographic uniqueness point of the item."
+        },
+        "massiveauditorylexicaldecision_PhonND": {
+          "description": "The number of phonological neighbors (one phone edit away)."
+        },
+        "massiveauditorylexicaldecision_OrthND": {
+          "description": "The number of orthographic neighbors (one glyph edit away)."
+        },
+        "massiveauditorylexicaldecision_POS": {
+          "description": "The frequency-dominant part-of-speech of the orthographic form."
+        },
+        "massiveauditorylexicaldecision_AllPOS": {
+          "description": "All parts-of-speech of the orthographic wordform."
+        },
+        "massiveauditorylexicaldecision_FreqSUBTLEX": {
+          "description": "The frequency of the orthographic word form (SUBTLEX-US corpus)."
+        },
+        "massiveauditorylexicaldecision_FreqCOCA": {
+          "description": "Word frequency in the COCA corpus."
+        },
+        "massiveauditorylexicaldecision_FreqCOCAspok": {
+          "description": "Word frequency in the spoken language subset of the COCA corpus."
+        },
+        "massiveauditorylexicaldecision_FreqGoogle": {
+          "description": "Word frequency in the Google Unigram corpus."
+        },
+        "massiveauditorylexicaldecision_PhonUP": {
+          "description": "The phone index of the phonological uniqueness point of the item."
+        },
+        "massiveauditorylexicaldecision_StressCat": {
+          "description": "The stress category of word items."
+        },
+        "massiveauditorylexicaldecision_PhonLev": {
+          "description": "Mean phone-level Levenshtein distance from all entries in CMU-A."
+        },
+        "massiveauditorylexicaldecision_NumMorphs": {
+          "description": "The number of morphemes."
+        },
+        "massiveauditorylexicaldecision_OrthLev": {
+          "description": "Mean orthographic Levenshtein distance from all entries in CMU-A."
+        },
+        "calgarysemanticdecision_Concrete_rating": {
+          "description": "Concreteness (calgarysemanticdecision)."
         }
       }
     }