Updated tutorials for 4.1 release.

oracle · May 26, 2021 · a899b90 · a899b90
1 parent 2f1969b
commit a899b90
Show file tree

Hide file tree

Showing 9 changed files with 193 additions and 151 deletions.
diff --git a/tutorials/anomaly-tribuo-v4.ipynb b/tutorials/anomaly-tribuo-v4.ipynb
@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%jars ./tribuo-anomaly-libsvm-4.1.0-SNAPSHOT-jar-with-dependencies.jar"
+    "%jars ./tribuo-anomaly-libsvm-4.1.0-jar-with-dependencies.jar"
    ]
   },
   {
@@ -110,7 +110,7 @@
       "obj = 293.8182352369252, rho = 3.201748862633537\n",
       "nSV = 301, nBSV = 120\n",
       "\n",
-      "Training took (00:00:00:115)\n"
+      "Training took (00:00:00:149)\n"
      ]
     }
    ],
@@ -209,7 +209,7 @@
    "mimetype": "text/x-java-source",
    "name": "Java",
    "pygments_lexer": "java",
-   "version": "16+14"
+   "version": "17-ea+22-1964"
   }
  },
  "nbformat": 4,

diff --git a/tutorials/clustering-tribuo-v4.ipynb b/tutorials/clustering-tribuo-v4.ipynb
@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%jars ./tribuo-clustering-kmeans-4.1.0-SNAPSHOT-jar-with-dependencies.jar"
+    "%jars ./tribuo-clustering-kmeans-4.1.0-jar-with-dependencies.jar"
    ]
   },
   {
@@ -98,7 +98,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training with 5 clusters took (00:00:00:049)\n"
+      "Training with 5 clusters took (00:00:00:102)\n"
      ]
     }
    ],
@@ -175,7 +175,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training with 5 clusters took (00:00:00:042)\n"
+      "Training with 5 clusters took (00:00:00:074)\n"
      ]
     }
    ],
@@ -277,8 +277,8 @@
      "data": {
       "text/plain": [
        "Clustering Evaluation\n",
-       "Normalized MI = 0.8154291916732409\n",
-       "Adjusted MI = 0.8139169342020223"
+       "Normalized MI = 0.8154291916732408\n",
+       "Adjusted MI = 0.8139169342020222"
       ]
      },
      "execution_count": 10,
@@ -347,7 +347,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training with 5 clusters on 4 threads took (00:00:00:038)\n"
+      "Training with 5 clusters on 4 threads took (00:00:00:062)\n"
      ]
     }
    ],
@@ -376,7 +376,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training with 20 clusters on 4 threads took (00:00:00:038)\n"
+      "Training with 20 clusters on 4 threads took (00:00:00:080)\n"
      ]
     }
    ],
@@ -404,8 +404,8 @@
      "data": {
       "text/plain": [
        "Clustering Evaluation\n",
-       "Normalized MI = 0.8104463467727059\n",
-       "Adjusted MI = 0.8088941747451209"
+       "Normalized MI = 0.8104463467727057\n",
+       "Adjusted MI = 0.8088941747451207"
       ]
      },
      "execution_count": 14,
@@ -478,7 +478,7 @@
    "mimetype": "text/x-java-source",
    "name": "Java",
    "pygments_lexer": "java",
-   "version": "16+14"
+   "version": "17-ea+22-1964"
   }
  },
  "nbformat": 4,

diff --git a/tutorials/columnar-tribuo-v4.ipynb b/tutorials/columnar-tribuo-v4.ipynb
@@ -38,8 +38,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%jars ./tribuo-classification-experiments-4.1.0-SNAPSHOT-jar-with-dependencies.jar\n",
-    "%jars ./tribuo-json-4.1.0-SNAPSHOT-jar-with-dependencies.jar"
+    "%jars ./tribuo-classification-experiments-4.1.0-jar-with-dependencies.jar\n",
+    "%jars ./tribuo-json-4.1.0-jar-with-dependencies.jar"
    ]
   },
   {
@@ -527,7 +527,7 @@
     {
      "data": {
       "text/plain": [
-       "Prediction(maxLabel=(BAD,0.9679724514693198),outputScores={BAD=(BAD,0.9679724514693198)GOOD=(GOOD,0.03202754853068015})"
+       "Prediction(maxLabel=(BAD,0.96797245146932),outputScores={BAD=(BAD,0.96797245146932),GOOD=(GOOD,0.032027548530680135)})"
       ]
      },
      "execution_count": 20,
@@ -568,7 +568,7 @@
    "mimetype": "text/x-java-source",
    "name": "Java",
    "pygments_lexer": "java",
-   "version": "16+14"
+   "version": "17-ea+22-1964"
   }
  },
  "nbformat": 4,

diff --git a/tutorials/configuration-tribuo-v4.ipynb b/tutorials/configuration-tribuo-v4.ipynb
@@ -32,8 +32,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%jars ./tribuo-classification-experiments-4.1.0-SNAPSHOT-jar-with-dependencies.jar\n",
-    "%jars ./tribuo-json-4.1.0-SNAPSHOT-jar-with-dependencies.jar"
+    "%jars ./tribuo-classification-experiments-4.1.0-jar-with-dependencies.jar\n",
+    "%jars ./tribuo-json-4.1.0-jar-with-dependencies.jar"
    ]
   },
   {
@@ -404,7 +404,7 @@
     {
      "data": {
       "text/plain": [
-       "XGBoostTrainer(numTrees=10,parameters{colsample_bytree=1.0, silent=1, seed=1, max_depth=4, booster=gbtree, objective=multi:softprob, lambda=1.0, eta=0.5, nthread=6, alpha=1.0, subsample=1.0, gamma=0.1, min_child_weight=1.0})"
+       "XGBoostTrainer(numTrees=10,parameters{colsample_bytree=1.0, tree_method=auto, seed=1, max_depth=4, booster=gbtree, objective=multi:softprob, lambda=1.0, eta=0.5, nthread=6, alpha=1.0, subsample=1.0, gamma=0.1, min_child_weight=1.0, verbosity=0})"
       ]
      },
      "execution_count": 11,
@@ -487,7 +487,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training logistic regression took (00:00:05:071)\n"
+      "Training logistic regression took (00:00:03:669)\n"
      ]
     }
    ],
@@ -569,8 +569,8 @@
        "        \"shuffle\" : \"true\",\n",
        "        \"epochs\" : \"2\",\n",
        "        \"optimiser\" : \"adagrad-2\",\n",
-       "        \"objective\" : \"logmulticlass-3\",\n",
-       "        \"loggingInterval\" : \"10000\"\n",
+       "        \"loggingInterval\" : \"10000\",\n",
+       "        \"objective\" : \"logmulticlass-3\"\n",
        "      }\n",
        "    }, {\n",
        "      \"name\" : \"adagrad-2\",\n",
@@ -805,7 +805,7 @@
       "\t\t\t\t\t\t\tfeaturesPath = /Users/apocock/Development/Tribuo/tutorials/train-images-idx3-ubyte.gz\n",
       "\t\t\t\t\t\t\tfeatures-file-modified-time = 2000-07-21T14:20:24-04:00\n",
       "\t\t\t\t\t\t\toutput-resource-hash = 3552534A0A558BBED6AED32B30C495CCA23D567EC52CAC8BE1A0730E8010255C\n",
-      "\t\t\t\t\t\t\tdatasource-creation-time = 2020-11-02T16:58:33.387902-05:00\n",
+      "\t\t\t\t\t\t\tdatasource-creation-time = 2021-05-24T12:24:14.958637-04:00\n",
       "\t\t\t\t\t\t\toutput-file-modified-time = 2000-07-21T14:20:27-04:00\n",
       "\t\t\t\t\t\t\tidx-feature-type = UBYTE\n",
       "\t\t\t\t\t\t\tfeatures-resource-hash = 440FCABF73CC546FA21475E81EA370265605F56BE210A4024D2CA8F203523609\n",
@@ -817,7 +817,7 @@
       "\t\t\t\t\tnum-examples = 60000\n",
       "\t\t\t\t\tnum-features = 717\n",
       "\t\t\t\t\tnum-outputs = 10\n",
-      "\t\t\t\t\ttribuo-version = 4.1.0-SNAPSHOT\n",
+      "\t\t\t\t\ttribuo-version = 4.1.0\n",
       "\t\t\t\t)\n",
       "\t\t\ttrainer = LinearSGDTrainer(\n",
       "\t\t\t\t\tclass-name = org.tribuo.classification.sgd.linear.LinearSGDTrainer\n",
@@ -832,20 +832,24 @@
       "\t\t\t\t\t\t\tinitialValue = 0.0\n",
       "\t\t\t\t\t\t\thost-short-name = StochasticGradientOptimiser\n",
       "\t\t\t\t\t\t)\n",
+      "\t\t\t\t\tloggingInterval = 10000\n",
       "\t\t\t\t\tobjective = LogMulticlass(\n",
       "\t\t\t\t\t\t\tclass-name = org.tribuo.classification.sgd.objectives.LogMulticlass\n",
       "\t\t\t\t\t\t\thost-short-name = LabelObjective\n",
       "\t\t\t\t\t\t)\n",
-      "\t\t\t\t\tloggingInterval = 10000\n",
+      "\t\t\t\t\ttribuo-version = 4.1.0\n",
       "\t\t\t\t\ttrain-invocation-count = 0\n",
       "\t\t\t\t\tis-sequence = false\n",
       "\t\t\t\t\thost-short-name = Trainer\n",
       "\t\t\t\t)\n",
-      "\t\t\ttrained-at = 2020-11-02T16:58:40.405866-05:00\n",
+      "\t\t\ttrained-at = 2021-05-24T12:24:19.604718-04:00\n",
       "\t\t\tinstance-values = Map{\n",
       "\t\t\t\treconfigured-model=true\n",
       "\t\t\t}\n",
-      "\t\t\ttribuo-version = 4.1.0-SNAPSHOT\n",
+      "\t\t\ttribuo-version = 4.1.0\n",
+      "\t\t\tjava-version = 17-ea\n",
+      "\t\t\tos-name = Mac OS X\n",
+      "\t\t\tos-arch = x86_64\n",
       "\t\t)\n",
       "\tdataset-provenance = MutableDataset(\n",
       "\t\t\tclass-name = org.tribuo.MutableDataset\n",
@@ -858,7 +862,7 @@
       "\t\t\t\t\tfeaturesPath = /Users/apocock/Development/Tribuo/tutorials/t10k-images-idx3-ubyte.gz\n",
       "\t\t\t\t\tfeatures-file-modified-time = 2000-07-21T14:19:56-04:00\n",
       "\t\t\t\t\toutput-resource-hash = F7AE60F92E00EC6DEBD23A6088C31DBD2371ECA3FFA0DEFAEFB259924204AEC6\n",
-      "\t\t\t\t\tdatasource-creation-time = 2020-11-02T16:58:20.304804-05:00\n",
+      "\t\t\t\t\tdatasource-creation-time = 2021-05-24T12:24:03.396403-04:00\n",
       "\t\t\t\t\toutput-file-modified-time = 2000-07-21T14:20:05-04:00\n",
       "\t\t\t\t\tidx-feature-type = UBYTE\n",
       "\t\t\t\t\tfeatures-resource-hash = 8D422C7B0A1C1C79245A5BCF07FE86E33EEAFEE792B84584AEC276F5A2DBC4E6\n",
@@ -870,9 +874,9 @@
       "\t\t\tnum-examples = 10000\n",
       "\t\t\tnum-features = 668\n",
       "\t\t\tnum-outputs = 10\n",
-      "\t\t\ttribuo-version = 4.1.0-SNAPSHOT\n",
+      "\t\t\ttribuo-version = 4.1.0\n",
       "\t\t)\n",
-      "\ttribuo-version = 4.1.0-SNAPSHOT\n",
+      "\ttribuo-version = 4.1.0\n",
       ")\n"
      ]
     }
@@ -900,7 +904,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training transformed logistic regression took (00:00:09:194)\n"
+      "Training transformed logistic regression took (00:00:05:252)\n"
      ]
     }
    ],
@@ -1018,15 +1022,16 @@
        "        \"shuffle\" : \"true\",\n",
        "        \"epochs\" : \"2\",\n",
        "        \"optimiser\" : \"adagrad-5\",\n",
-       "        \"objective\" : \"logmulticlass-6\",\n",
-       "        \"loggingInterval\" : \"10000\"\n",
+       "        \"loggingInterval\" : \"10000\",\n",
+       "        \"objective\" : \"logmulticlass-6\"\n",
        "      }\n",
        "    }, {\n",
        "      \"name\" : \"transformtrainer-0\",\n",
        "      \"type\" : \"org.tribuo.transform.TransformTrainer\",\n",
        "      \"export\" : \"false\",\n",
        "      \"import\" : \"false\",\n",
        "      \"properties\" : {\n",
+       "        \"includeImplicitZeroFeatures\" : \"false\",\n",
        "        \"transformations\" : \"transformationmap-1\",\n",
        "        \"densify\" : \"false\",\n",
        "        \"innerTrainer\" : \"linearsgdtrainer-2\"\n",
@@ -1106,7 +1111,7 @@
    "mimetype": "text/x-java-source",
    "name": "Java",
    "pygments_lexer": "java",
-   "version": "16+14"
+   "version": "17-ea+22-1964"
   }
  },
  "nbformat": 4,

diff --git a/tutorials/document-classification-tribuo-v4.ipynb b/tutorials/document-classification-tribuo-v4.ipynb
@@ -49,8 +49,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%jars ./tribuo-classification-experiments-4.1.0-SNAPSHOT-jar-with-dependencies.jar\n",
-    "%jars ./tribuo-onnx-4.1.0-SNAPSHOT-jar-with-dependencies.jar"
+    "%jars ./tribuo-classification-experiments-4.1.0-jar-with-dependencies.jar\n",
+    "%jars ./tribuo-onnx-4.1.0-jar-with-dependencies.jar"
    ]
   },
   {
@@ -198,7 +198,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training the model on BoW features took (00:00:09:366)\n",
+      "Training the model on BoW features took (00:00:09:659)\n",
       "\n",
       "Class                                n          tp          fn          fp      recall        prec          f1\n",
       "soc.religion.christian             398         352          46         110       0.884       0.762       0.819\n",
@@ -291,7 +291,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training the model on Unigram features took (00:00:09:556)\n",
+      "Training the model on Unigram features took (00:00:10:529)\n",
       "\n",
       "Class                                n          tp          fn          fp      recall        prec          f1\n",
       "soc.religion.christian             398         362          36          88       0.910       0.804       0.854\n",
@@ -381,7 +381,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training the model on Bigram features took (00:00:46:003)\n",
+      "Training the model on Bigram features took (00:00:41:981)\n",
       "\n",
       "Class                                n          tp          fn          fp      recall        prec          f1\n",
       "soc.religion.christian             398         331          67          57       0.832       0.853       0.842\n",
@@ -480,7 +480,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training the model on TF-IDF features took (00:00:41:742)\n",
+      "Training the model on TF-IDF features took (00:00:42:471)\n",
       "\n",
       "Class                                n          tp          fn          fp      recall        prec          f1\n",
       "soc.religion.christian             398         350          48         183       0.879       0.657       0.752\n",
@@ -570,7 +570,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training the model on hashed features took (00:00:23:394)\n",
+      "Training the model on hashed features took (00:00:24:289)\n",
       "\n",
       "Class                                n          tp          fn          fp      recall        prec          f1\n",
       "soc.religion.christian             398         306          92         125       0.769       0.710       0.738\n",
@@ -662,7 +662,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training the model on trimmed TF-IDF features took (00:00:19:872)\n",
+      "Training the model on trimmed TF-IDF features took (00:00:19:049)\n",
       "\n",
       "Class                                n          tp          fn          fp      recall        prec          f1\n",
       "soc.religion.christian             398         337          61          93       0.847       0.784       0.814\n",
@@ -750,7 +750,7 @@
      "text": [
       "bert training data size = 11314, number of features = 768, number of classes = 20\n",
       "bert testing data size = 7532, number of features = 768, number of classes = 20\n",
-      "Extracting features with BERT took (00:59:31:085)\n"
+      "Extracting features with BERT took (01:06:52:756)\n"
      ]
     }
    ],
@@ -789,7 +789,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training a LR on BERT features took (00:00:06:870)\n",
+      "Training a LR on BERT features took (00:00:08:960)\n",
       "Class                                n          tp          fn          fp      recall        prec          f1\n",
       "soc.religion.christian             398         353          45         111       0.887       0.761       0.819\n",
       "rec.autos                          396         332          64          99       0.838       0.770       0.803\n",
@@ -880,7 +880,7 @@
       "\t\t\tclass-name = org.tribuo.classification.LabelFactory\n",
       "\t\t)\n",
       "\tfile-modified-time = 2003-03-18T07:24:55-05:00\n",
-      "\tdatasource-creation-time = 2021-05-21T10:33:44.926193-04:00\n",
+      "\tdatasource-creation-time = 2021-05-24T12:46:58.801385-04:00\n",
       ")\n"
      ]
     }

diff --git a/tutorials/external-models-tribuo-v4.ipynb b/tutorials/external-models-tribuo-v4.ipynb
@@ -24,8 +24,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%jars tribuo-classification-experiments-4.1.0-SNAPSHOT-jar-with-dependencies.jar\n",
-    "%jars tribuo-onnx-4.1.0-SNAPSHOT-jar-with-dependencies.jar"
+    "%jars tribuo-classification-experiments-4.1.0-jar-with-dependencies.jar\n",
+    "%jars tribuo-onnx-4.1.0-jar-with-dependencies.jar"
    ]
   },
   {
@@ -469,7 +469,7 @@
    "mimetype": "text/x-java-source",
    "name": "Java",
    "pygments_lexer": "java",
-   "version": "16+14"
+   "version": "17-ea+22-1964"
   }
  },
  "nbformat": 4,