refining LinesFactoryTest

src/HowBadIsMyBatch.ipynb

@@ -666,9 +666,7 @@
    "source": [
     "from SymptomsCausedByVaccines.MultiLineFitting.MultiLineFitter import MultiLineFitter\n",
     "from SymptomsCausedByVaccines.MultiLineFitting.SymptomCombinationsProvider import SymptomCombinationsProvider\n",
-    "import numpy as np\n",
-    "from matplotlib import pyplot as plt\n",
-    "from skspatial.objects import Line\n"
+    "from matplotlib import pyplot as plt\n"
    ]
   },
   {
@@ -677,8 +675,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "symptomX = 'Abdominal abscess' # HIV test' # 'Immunosuppression'\n",
-    "symptomY = 'Abdominal discomfort' # 'Infection' # 'Immunoglobulin therapy'"
+    "# symptomX = 'Abdominal discomfort' # HIV test' # 'Immunosuppression'\n",
+    "# symptomY = 'Abdominal distension' # 'Infection' # 'Immunoglobulin therapy'"
    ]
   },
   {
@@ -687,9 +685,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df = prrByLotAndSymptom[[symptomX, symptomY]]\n",
-    "df = df[(df[symptomX] != 0) & (df[symptomY] != 0)]\n",
-    "df"
+    "# df = prrByLotAndSymptom[[symptomX, symptomY]]\n",
+    "# df = df[(df[symptomX] != 0) & (df[symptomY] != 0)]\n",
+    "# df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# retain only those columns of prrByLotAndSymptom that have more than 400 PRRs != 0\n",
+    "# prrByLotAndSymptom2 = prrByLotAndSymptom.loc[:, (prrByLotAndSymptom != 0).sum() >= 400]\n",
+    "# prrByLotAndSymptom2"
    ]
   },
   {
@@ -699,8 +708,8 @@
    "outputs": [],
    "source": [
     "symptomCombinations = SymptomCombinationsProvider.generateSymptomCombinations(\n",
-    "    prrByLotAndSymptom[prrByLotAndSymptom.columns[:500]],\n",
-    "    dataFramePredicate = lambda df: 30 <= len(df) <= 35)"
+    "    prrByLotAndSymptom,\n",
+    "    dataFramePredicate = lambda df: 40 <= len(df) <= 50)"
    ]
   },
   {
@@ -709,8 +718,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "for symptomCombination in symptomCombinations:\n",
-    "    print(list(symptomCombination.columns))"
+    "from SymptomsCausedByVaccines.MultiLineFitting.Utils import take\n",
+    "\n",
+    "df = take(symptomCombinations, 1)[0]\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "symptomX, symptomY = df.columns"
    ]
   },
   {
@@ -758,7 +778,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "clustersAscending, linesAscending = MultiLineFitter.fitPointsByAscendingLines(points, consensusThreshold = 0.001)"
+    "clustersAscending, linesAscending = MultiLineFitter.fitPointsByAscendingLines(\n",
+    "    points,\n",
+    "    consensusThreshold = 0.01,\n",
+    "    maxNumLines = None)"
    ]
   },
   {
@@ -767,7 +790,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "draw(points, clustersAscending, linesAscending, symptomX, symptomY, minClusterSize = 2)"
+    "draw(points, clustersAscending, linesAscending, symptomX, symptomY, minClusterSize = 5)"
    ]
   },
   {
@@ -776,7 +799,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "clusters, lines = MultiLineFitter.fitPointsByLines(points, consensusThreshold = 0.1)"
+    "clusters, lines = MultiLineFitter.fitPointsByLines(\n",
+    "    points,\n",
+    "    consensusThreshold = 0.01,\n",
+    "    maxNumLines = None)"
    ]
   },
   {