teradataml 20.0.0.0__py3-none-any.whl → 20.0.0.1__py3-none-any.whl

teradataml/data/jsons/sqle/17.20/TD_XGBoostPredict.json

@@ -79,7 +79,7 @@
       "lowerBoundType": "EXCLUSIVE",
       "upperBoundType": "INCLUSIVE",
       "allowNaN": false,
-      "name": "NumBoostedTrees",
+      "name": "NumParallelTrees",
       "alternateNames": [], 
       "isRequired": false,
       "defaultValue": 1000,
@@ -97,10 +97,10 @@
       "lowerBoundType": "EXCLUSIVE",
       "upperBoundType": "INCLUSIVE",
       "allowNaN": false,
-      "name": "IterNum",
+      "name": "NumBoostRounds",
       "alternateNames": [], 
       "isRequired": false,
-      "defaultValue": 3,
+      "defaultValue": 10,
       "rDescription": "Specify number of iterations within a boosted trees to be loaded from model table", 
       "description": "Specify number of iterations within a boosted trees to be loaded from model table",
       "datatype": "NUMERIC",
@@ -177,6 +177,19 @@
       "rName": "output.responses",
       "useInR": true,
       "rOrderNum": 9
+    },
+    {
+      "defaultValue": false,
+      "name": "Detailed",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies whether to output detailed information of each prediction.",
+      "description": "Specifies whether to output detailed information of each prediction.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "detailed",
+      "useInR": true,
+      "rOrderNum": 10
     }
   ]
-}
+}

teradataml/data/jsons/sqle/17.20/TD_ZTest.json

@@ -1,26 +1,27 @@
 {
   "json_schema_major_version": "1",
-  "json_schema_minor_version": "1",
-  "json_content_version": "1",
+  "json_schema_minor_version": "2",
+  "json_content_version": "2",
   "function_name": "TD_ZTest",
-  "function_version": "1.0",
+  "function_alias_name": "TD_ZTest",
+  "function_version": "2.0",
+  "commence_db_version" : "17.20",
+  "change_db_version" : "17.20.03.XX",
   "function_type": "fastpath",
   "function_category": "Hypothesis Testing",
-  "function_alias_name": "TD_ZTest",
   "function_r_name": "aa.td_ztest",
   "short_description": "hypothesis test function to perform ztest analysis on a data set.",
   "long_description": "fastpath function to perform ztest analysis on a data set.",
   "input_tables": [
     {
-      "isOrdered": false,
-      "partitionByOne": false,
       "name": "InputTable",
       "alternateNames": [],
       "isRequired": true,
-      "rDescription": "The input table for ztest analysis",
-      "description": "The input table for ztest analysis.",
       "datatype": "TABLE_ALIAS",
-      "allowsLists": false,
+      "partitionByOne": false,
+      "isOrdered": false,
+      "description": "The input table for ztest analysis.",
+      "rDescription": "The input table for ztest analysis",
       "rName": "data",
       "useInR": true,
       "rOrderNum": 1
@@ -28,27 +29,30 @@
   ],
   "argument_clauses": [
     {
-      "defaultValue": 0.5,
-      "lowerBound": 0,
-      "upperBound": 1,
-      "lowerBoundType": "INCLUSIVE",
-      "upperBoundType": "INCLUSIVE",
-      "allowNaN": false,
-      "isOutputColumn": false,
-      "matchLengthOfArgument": "",
-      "allowPadding": false,
-      "name": "Alpha",
+      "name": "FirstSampleColumn",
       "alternateNames": [],
       "isRequired": false,
-      "rDescription": "Specifies the value of alpha in hypothesis test  function",
-      "description": "Specifies the value of alpha in hypothesis test function",
-      "datatype": "double precision",
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "NUMERIC"
+      ],
+      "rOrderNum": 2,
+      "description": "Specifies the first sample column in z test",
+      "rDescription": "Specifies the first sample column in z test",
+      "datatype": "COLUMNS",
       "allowsLists": false,
-      "rName": "alpha",
+      "rName": "first.sample.column",
       "useInR": true,
-      "rOrderNum": 2
+      "rFormulaUsage" : false
     },
     {
+      "name": "SecondSampleColumn",
+      "alternateNames": [],
+      "isRequired": false,
       "targetTable": [
         "InputTable"
       ],
@@ -57,22 +61,39 @@
       "allowedTypeGroups": [
         "NUMERIC"
       ],
-      "allowNaN": false,
-      "isOutputColumn": false,
-      "matchLengthOfArgument": "",
-      "allowPadding": false,
-      "name": "FirstSampleColumn",
-      "alternateNames": [],
-      "isRequired": true,
-      "rDescription": "Specifies the first sample column in f test",
-      "description": "Specifies the first sample column in f test",
-      "datatype": "COLUMN",
+      "rOrderNum": 3,
+      "description": "Specifies the second sample column in z test",
+      "rDescription": "Specifies the second sample column in z test",
+      "datatype": "COLUMNS",
       "allowsLists": false,
-      "rName": "first.sample.column",
+      "rName": "second.sample.column",
       "useInR": true,
-      "rOrderNum": 3
+      "rFormulaUsage" : false
     },
     {
+      "name": "SampleNameColumn",
+      "alternateNames": [],
+      "isRequired": false,
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "STRING"
+      ],
+      "rOrderNum": 4,
+      "description": "Specifies the input table column containing the names of the samples included in the z test. This argument is used when Input is in sample-value format.", 
+      "rDescription": "Specifies the input table column containing the names of the samples included in the z test. This argument is used when Input is in sample-value format.",
+      "datatype": "COLUMNS",
+      "allowsLists": false,
+      "rName": "sample.name.column",
+      "useInR": true
+    },
+    {
+      "name": "SampleValueColumn",
+      "alternateNames": [],
+      "isRequired": false,
       "targetTable": [
         "InputTable"
       ],
@@ -81,90 +102,146 @@
       "allowedTypeGroups": [
         "NUMERIC"
       ],
-      "allowNaN": false,
-      "isOutputColumn": false,
-      "matchLengthOfArgument": "",
-      "allowPadding": false,
-      "name": "SecondSampleColumn",
+      "rOrderNum": 5,
+      "description": "Specifies the input table column containing the values for each sample member. This argument is used when Input is in sample-value format.",
+      "rDescription": "Specifies the input table column containing the values for each sample member. This argument is used when Input is in sample-value format.",
+      "datatype": "COLUMNS",
+      "allowsLists": false,
+      "rName": "sample.value.column",
+      "useInR": true
+    },
+    {
+      "name": "FirstSampleName",
       "alternateNames": [],
       "isRequired": false,
-      "rDescription": "Specifies the second sample column in f test",
-      "description": "Specifies the second sample column in f test",
-      "datatype": "COLUMN",
+      "defaultValue" : "",
+      "rOrderNum": 6,
+      "description": "Specifies the name of the first sample included in the z test. This argument is used when Input is in sample-value format.",
+      "rDescription": "Specifies the name of the first sample included in the z test. This argument is used when Input is in sample-value format.",
+      "datatype": "STRING",
       "allowsLists": false,
-      "rName": "second.sample.column",
+      "allowPadding": false,
+      "rName": "first.sample.name",
       "useInR": true,
-      "rOrderNum": 4
+      "rDefaultValue" : ""
     },
     {
-       "permittedValues": [
-        "lower-tailed",
-        "two-tailed",
-        "upper-tailed"
-       ],
-      "defaultValue": "two-tailed",
-      "allowNaN": false,
-      "isOutputColumn": false,
-      "matchLengthOfArgument": "",
-      "allowPadding": false,
-      "name": "Alternatehypothesis",
+      "name": "SecondSampleName",
       "alternateNames": [],
       "isRequired": false,
-      "rDescription": "Specifies the alternate hypothesis",
-      "description": "Specifies the alternate hypothesis",
+      "defaultValue" : "",
+      "rOrderNum": 7,
+      "description": "Specifies the name of the second sample included in the z test. This argument is used when Input is in sample-value format.",
+      "rDescription": "Specifies the name of the second sample included in the z test. This argument is used when Input is in sample-value format.",
       "datatype": "STRING",
       "allowsLists": false,
-      "rName": "alternate.hypothesis",
+      "allowPadding": false,
+      "rName": "second.sample.name",
       "useInR": true,
-      "rOrderNum": 5
+      "rDefaultValue" : ""
     },
     {
+      "name": "FirstSampleVariance",
+      "alternateNames": [],
+      "isRequired": false,
+      "rOrderNum": 8,
+      "lowerBound" : 0,
+      "lowerBoundType" : "EXCLUSIVE",
+      "upperBound" : 1e10,
+      "upperBoundType" : "EXCLUSIVE",
       "allowNaN": false,
       "isOutputColumn": false,
       "matchLengthOfArgument": "",
-      "allowPadding": false,
-      "name": "FirstSampleVariance",
-      "alternateNames": [],
-      "isRequired": true,
-      "rDescription": "Specifies the first sample variance",
       "description": "Specifies the first sample variance",
-      "datatype": "NUMERIC",
+      "rDescription": "Specifies the first sample variance",
+      "datatype": "DOUBLE",
       "allowsLists": false,
+      "allowPadding": false,
       "rName": "first.sample.variance",
       "useInR": true,
-      "rOrderNum": 6
+      "rDefaultValue" : ""
     },
     {
-      "allowNaN": false,
-      "isOutputColumn": false,
-      "matchLengthOfArgument": "",
-      "allowPadding": false,
       "name": "SecondSampleVariance",
       "alternateNames": [],
       "isRequired": false,
-      "rDescription": "Specifies the second sample variance",
+      "rOrderNum": 9,
+      "lowerBound" : 0,
+      "lowerBoundType" : "EXCLUSIVE",
+      "upperBound" : 1e10,
+      "upperBoundType" : "EXCLUSIVE",
+      "allowNaN": false,
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
       "description": "Specifies the second sample variance",
-      "datatype": "NUMERIC",
+      "rDescription": "Specifies the second sample variance",
+      "datatype": "DOUBLE",
       "allowsLists": false,
+      "allowPadding": false,
       "rName": "second.sample.variance",
       "useInR": true,
-      "rOrderNum": 7
+      "rDefaultValue" : ""
     },
     {
-      "allowNaN": false,
-      "isOutputColumn": false,
+      "name": "AlternativeHypothesis",
+      "alternateNames": [],
+      "isRequired": false,
+      "defaultValue": "two-tailed",
+      "rOrderNum": 10,
+      "permittedValues": [
+        "lower-tailed",
+        "two-tailed",
+        "upper-tailed"
+       ],
       "matchLengthOfArgument": "",
+      "description": "Specifies the alternative hypothesis",
+      "rDescription": "Specifies the alternative hypothesis",
+      "datatype": "STRING",
+      "allowsLists": false,
       "allowPadding": false,
+      "rName": "alternate.hypothesis",
+      "useInR": true,
+      "rDefaultValue" : ""
+    },
+    {
       "name": "MeanUnderH0",
       "alternateNames": [],
       "isRequired": false,
-      "rDescription": "Specifies the mean under the null hypothesis",
+      "defaultValue": 0,
+      "rOrderNum": 11,
+      "lowerBound": 0,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBound": 1,
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
       "description": "Specifies the mean under the null hypothesis",
+      "rDescription": "Specifies the mean under the null hypothesis",
       "datatype": "NUMERIC",
       "allowsLists": false,
+      "allowPadding": false,
       "rName": "mean.under.h0",
       "useInR": true,
-      "rOrderNum": 8
+      "rDefaultValue" : ""
+    },
+    {
+      "name": "Alpha",
+      "alternateNames": [],
+      "isRequired": false,
+      "defaultValue": 0.05,
+      "rOrderNum": 12,
+      "lowerBound": 0,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBound": 1,
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "description": "Specifies the value of alpha in hypothesis test function",
+      "rDescription": "Specifies the value of alpha in hypothesis test function",
+      "datatype": "DOUBLE",
+      "allowsLists": false,
+      "allowPadding": false,
+      "rName": "alpha",
+      "useInR": true,
+      "rDefaultValue" : ""
     }
   ]
-}
+}

teradataml/data/kmeans_example.json

@@ -14,5 +14,10 @@
     "assault": "real",
     "urban_pop": "integer",
     "rape": "real"
+  },
+  "kmeans_table":{
+    "id":"integer",
+    "c1":"integer",
+    "c2":"integer"
   }
 }

teradataml/data/kmeans_table.csv

@@ -0,0 +1,10 @@
+id,c1,c2
+5,56,56
+9,90,90
+7,88,88
+6,57,57
+3,20,20
+4,55,55
+1,18,18
+8,89,89
+2,19,19

teradataml/data/onehot_encoder_train.csv

@@ -0,0 +1,4 @@
+gender,numb
+Male,1
+Female,3
+Female,2

teradataml/data/openml_example.json

@@ -59,5 +59,34 @@
         "group_column" : "integer",
         "partition_column_1" : "integer",
         "partition_column_2" : "integer"
+    },
+    "onehot_encoder_train": {
+        "gender" : "varchar(20)",
+        "numb" : "integer"
+    },
+    "customer_segmentation_train": {
+        "ID" : "integer",
+        "Gender" : "varchar(10)",
+        "Ever_Married" : "varchar(10)",
+        "Age" : "integer",
+        "Graduated" : "varchar(10)",
+        "Profession" : "varchar(30)",
+        "Work_Experience" : "integer",
+        "Spending_Score" : "varchar(10)",
+        "Family_Size": "integer",
+        "Var_1": "varchar(10)",
+        "Segmentation": "varchar(2)"
+    },
+    "customer_segmentation_test": {
+        "ID" : "integer",
+        "Gender" : "varchar(10)",
+        "Ever_Married" : "varchar(10)",
+        "Age" : "integer",
+        "Graduated" : "varchar(10)",
+        "Profession" : "varchar(30)",
+        "Work_Experience" : "integer",
+        "Spending_Score" : "varchar(10)",
+        "Family_Size": "integer",
+        "Var_1": "varchar(10)"
     }
 }

teradataml/data/scale_attributes.csv

@@ -0,0 +1,3 @@
+pid,attribute_column
+1,fare
+2,age

teradataml/data/scale_example.json

@@ -19,5 +19,56 @@
                   "bathrms" : "real",
                   "stories" : "real"
                   
-        }
+        },
+"scale_attributes":{
+                   
+                   "pid" : "integer",
+                   "attribute_column" : "varchar(150)"
+                   
+           },
+"scale_parameters":{
+                   
+                   "pid" : "integer",
+                   "parameter_column" : "varchar(150)",
+                   "value_column" : "varchar(150)"
+                   
+           },
+"scale_input_partitioned":{
+                        "passenger" : "integer",
+                        "pid" : "integer",
+                        "survived" : "integer",
+                        "pclass" : "integer",
+                        "name" : "varchar(90)",
+                        "gender" : "varchar(10)",
+                        "age" : "integer",
+                        "sibsp" : "integer",
+                        "parch" : "integer",
+                        "ticket" : "varchar(20)",
+                        "fare" : "integer",
+                        "cabin" : "varchar(20)",
+                        "embarked" : "varchar(10)"
+
+
+},
+
+"scale_input_sparse":
+{
+                   
+        "passenger" : "integer",
+        "attribute_column" : "varchar(20)",
+        "attribute_value" : "real"
+                   
+},
+
+"scale_input_part_sparse":
+{
+                   
+        "pid" : "integer",
+        "passenger" : "integer",
+        "attribute_column" : "varchar(20)",
+        "attribute_value" : "real"
+                   
 }
+
+        
+}

teradataml/data/scale_input_part_sparse.csv

@@ -0,0 +1,31 @@
+pid,passenger,attribute_column,attribute_value
+3,56,age,
+3,56,fare,35.5
+3,63,age,45.0
+3,63,fare,83.475
+3,67,age,29.0
+3,67,fare,10.5
+3,76,age,25.0
+3,76,fare,7.65
+3,93,age,46.0
+3,93,fare,61.175
+1,2,age,38.0
+1,2,fare,71.2833
+1,4,age,35.0
+1,4,fare,53.1
+1,7,age,54.0
+1,7,fare,51.8625
+1,11,age,4.0
+1,11,fare,16.7
+1,12,age,58.0
+1,12,fare,26.55
+2,22,age,34.0
+2,22,fare,13.0
+2,24,age,28.0
+2,24,fare,35.5
+2,32,age,
+2,32,fare,146.5208
+2,53,age,49.0
+2,53,fare,76.7292
+2,55,age,65.0
+2,55,fare,61.9792

teradataml/data/scale_input_partitioned.csv

@@ -0,0 +1,16 @@
+passenger,pid,survived,pclass,name,gender,age,sibsp,parch,ticket,fare,cabin,embarked
+76,3,0,3,Moen; Mr. Sigurd Hansen,male,25.0,0,0,348123,7.65,F G73,S
+32,2,1,1,Spencer; Mrs. William Augustus (Marie Eugenie),female,,1,0,PC 17569,146.5208,B78,C
+55,2,0,1,Ostby; Mr. Engelhart Cornelius,male,65.0,0,1,113509,61.9792,B30,C
+53,2,1,1,Harper; Mrs. Henry Sleeper (Myna Haxtun),female,49.0,1,0,PC 17572,76.7292,D33,C
+93,3,0,1,Chaffee; Mr. Herbert Fuller,male,46.0,1,0,W.E.P. 5734,61.175,E31,S
+11,1,1,3,Sandstrom; Miss. Marguerite Rut,female,4.0,1,1,PP 9549,16.7,G6,S
+7,1,0,1,McCarthy; Mr. Timothy J,male,54.0,0,0,17463,51.8625,E46,S
+24,2,1,1,Sloper; Mr. William Thompson,male,28.0,0,0,113788,35.5,A6,S
+63,3,0,1,Harris; Mr. Henry Birkhardt,male,45.0,1,0,36973,83.475,C83,S
+22,2,1,2,Beesley; Mr. Lawrence,male,34.0,0,0,248698,13.0,D56,S
+56,3,1,1,Woolner; Mr. Hugh,male,,0,0,19947,35.5,C52,S
+12,1,1,1,Bonnell; Miss. Elizabeth,female,58.0,0,0,113783,26.55,C103,S
+2,1,1,1,Cumings; Mrs. John Bradley (Florence Briggs Thayer),female,38.0,1,0,PC 17599,71.2833,C85,C
+67,3,1,2,Nye; Mrs. (Elizabeth Ramell),female,29.0,0,0,C.A. 29395,10.5,F33,S
+4,1,1,1,Futrelle; Mrs. Jacques Heath (Lily May Peel),female,35.0,1,0,113803,53.1,C123,S

teradataml/data/scale_input_sparse.csv

@@ -0,0 +1,11 @@
+passenger,attribute_column,attribute_value
+873,age,33.0
+631,age,80.0
+97,age,71.0
+873,fare,5.0
+631,fare,30.0
+97,fare,34.6542
+488,age,58.0
+488,fare,29.7
+505,age,16.0
+505,fare,86.5

teradataml/data/scale_parameters.csv

@@ -0,0 +1,3 @@
+pid,parameter_column,value_column
+1,scalemethod,midrange
+2,scalemethod,range

teradataml/data/scripts/deploy_script.py

@@ -27,6 +27,11 @@ def get_values_list(values, ignore_none=True):
 
     return ret_vals
 
+if len(sys.argv) != 2:
+    sys.exit("Script command format: python deploy_script.py <enterprise/lake>")
+
+vantage_type = sys.argv[1]
+
 data_partition_column_values = []
 data_partition_column_indices = [5, 6]
 
@@ -60,6 +65,20 @@ y = np.array(labels)
 clf = make_pipeline(StandardScaler(), SVC(gamma='auto'))
 clf.fit(X, y)
 
-model = base64.b64encode(pickle.dumps(clf))
+model_str = pickle.dumps(clf)
+
+# Prepare the corresponding model file name and extract model.
+partition_join = "_".join([str(x) for x in data_partition_column_values])
+# Replace '-' with '_' as '-' because partition_columns can be negative.
+partition_join = partition_join.replace("-", "_")
+
+if vantage_type == "lake":
+    model = f"/tmp/sklearn_model_{partition_join}.pickle"
+    with open(model, "wb") as fp:
+        fp.write(model_str)
+elif vantage_type == "enterprise":
+    model = base64.b64encode(model_str)
+else:
+    sys.exit("Invalid vantage type. Use either 'lake' or 'enterprise'.")
 
 print(*(data_partition_column_values + [model]), sep=DELIMITER)