teradataml 20.0.0.4__py3-none-any.whl → 20.0.0.6__py3-none-any.whl

teradataml/data/tdnerextractor_example.json

@@ -0,0 +1,14 @@
+{
+    "ner_input_eng": {
+      "id": "integer",
+      "txt": "varchar(500)"
+    },
+    "ner_rule": {
+      "type_ner": "varchar(500)",
+      "regex": "varchar(500)"
+    },
+    "ner_dict": {
+      "type_ner": "varchar(500)",
+      "dict": "varchar(500)"
+    }
+  }

teradataml/data/teradataml_example.json

@@ -1356,6 +1356,10 @@
     "format_col": "VARCHAR(50)",
     "timezone_col": "VARCHAR(50)"
   },
+  "to_num_data":{
+    "price": "VARCHAR(20)",
+    "col_format": "VARCHAR(20)"
+  },
   "interval_data":{
     "id": "INTEGER",
     "int_col": "BIGINT",
@@ -1367,7 +1371,8 @@
   "url_data": {
     "id": "INTEGER",
     "urls": "VARCHAR(60)",
-    "part": "VARCHAR(20)"
+    "part": "VARCHAR(20)",
+    "query_key": "VARCHAR(20)"
   },
   "hnsw_data": {
     "id": "INTEGER",
@@ -1376,5 +1381,20 @@
   "hnsw_alter_data": {
     "id": "INTEGER",
     "array_col": "Vector"
+  },
+  "tochar_data": {
+    "id": "INTEGER",
+    "int_col": "INTEGER",
+    "float_col": "FLOAT",
+    "date_col": "DATE",
+    "int_format": "VARCHAR(20)",
+    "float_format": "VARCHAR(20)",
+    "date_format": "VARCHAR(20)"
+  },
+  "pattern_matching_data":{
+    "id": "INTEGER",
+    "data": "VARCHAR(20)",
+    "pattern": "VARCHAR(20)",
+    "level": "VARCHAR(20)"
   }
 }

teradataml/data/textmorph_example.json

@@ -2,5 +2,10 @@
   "words_input": {
     "id": "integer",
     "word": "varchar(30)"
+  },
+  "pos_input": {
+    "id": "integer",
+    "word": "varchar(100)",
+    "pos_tag": "varchar(100)"
   }
 }

teradataml/data/to_num_data.csv

@@ -0,0 +1,4 @@
+price,col_format
+"78.12","99.99"
+"USD123","C999"
+"$1234","$9999"

teradataml/data/tochar_data.csv

@@ -0,0 +1,5 @@
+id,int_col,float_col,date_col,int_format,float_format,date_format
+0,1234,234.56,03/09/17,"9,999","999D9","MM-DD"
+1,456,234.56,03/09/17,"$999","9.9EEEE","CCAD"
+2,789,123.46,03/09/17,"0999","9999.9","DAY"
+3,1314,123.46,03/09/17,"XXXX","TM9","DY"

teradataml/data/trans_dense.csv

@@ -0,0 +1,16 @@
+"location","tranid","period","storeid","region","item","sku","category"
+"MiddleEast",999,"20100715",1,"west","milk,butter,eggs,flour,spinach",1,"dairy"
+"MiddleEast",1000,"20100715",1,"west","milk,eggs,flour,spinach",1,"dairy"
+"MiddleEast",1001,"20100715",1,"west","milk,butter,eggs",1,"dairy"
+"MiddleEast",1002,"20100715",1,"west","milk,butter,spinach",1,"dairy"
+"MiddleEast",1500,"20100715",3,"west","butter,eggs,flour",2,"dairy"
+"AsiaPacific",999,"20100715",1,"west","milk,butter,eggs,flour,spinach",1,"dairy"
+"AsiaPacific",1000,"20100715",1,"west","milk,eggs,flour,spinach",1,"dairy"
+"AsiaPacific",1001,"20100715",1,"west","milk,butter,eggs",1,"dairy"
+"AsiaPacific",1002,"20100715",1,"west","milk,butter,spinach",1,"dairy"
+"AsiaPacific",1500,"20100715",3,"west","butter,eggs,flour",2,"dairy"
+"LatinAmerica",999,"20100715",1,"west","milk,butter,eggs,flour,spinach",1,"dairy"
+"LatinAmerica",1000,"20100715",1,"west","milk,eggs,flour,spinach",1,"dairy"
+"LatinAmerica",1001,"20100715",1,"west","milk,butter,eggs",1,"dairy"
+"LatinAmerica",1002,"20100715",1,"west","milk,butter,spinach",1,"dairy"
+"LatinAmerica",1500,"20100715",3,"west","butter,eggs,flour",2,"dairy"

teradataml/data/trans_sparse.csv

@@ -0,0 +1,55 @@
+"location","tranid","period","storeid","region","item","sku","category"
+"MiddleEast",999,"20100715",1,"west","milk",1,"dairy"
+"MiddleEast",999,"20100715",1,"west","butter",2,"dairy"
+"MiddleEast",999,"20100715",1,"west","eggs",3,"dairy"
+"MiddleEast",999,"19990715",1,"west","flour",4,"baking"
+"MiddleEast",999,"19990715",1,"west","spinach",4,"produce"
+"MiddleEast",1000,"20100715",1,"west","milk",1,"dairy"
+"MiddleEast",1000,"20100715",1,"west","eggs",3,"dairy"
+"MiddleEast",1000,"19990715",1,"west","flour",4,"baking"
+"MiddleEast",1000,"19990715",1,"west","spinach",2,"produce"
+"MiddleEast",1001,"20100715",1,"west","milk",1,"dairy"
+"MiddleEast",1001,"20100715",1,"west","butter",2,"dairy"
+"MiddleEast",1001,"20100715",1,"west","eggs",3,"dairy"
+"MiddleEast",1002,"20100715",1,"west","milk",1,"dairy"
+"MiddleEast",1002,"20100715",1,"west","butter",2,"dairy"
+"MiddleEast",1002,"20100715",1,"west","spinach",3,"produce"
+"MiddleEast",1500,"20100715",3,"west","butter",2,"dairy"
+"MiddleEast",1500,"20100715",3,"west","eggs",3,"dairy"
+"MiddleEast",1500,"20100715",3,"west","flour",4,"baking"
+"AsiaPacific",999,"20100715",1,"west","milk",1,"dairy"
+"AsiaPacific",999,"20100715",1,"west","butter",2,"dairy"
+"AsiaPacific",999,"20100715",1,"west","eggs",3,"dairy"
+"AsiaPacific",999,"19990715",1,"west","flour",4,"baking"
+"AsiaPacific",999,"19990715",1,"west","spinach",4,"produce"
+"AsiaPacific",1000,"20100715",1,"west","milk",1,"dairy"
+"AsiaPacific",1000,"20100715",1,"west","eggs",3,"dairy"
+"AsiaPacific",1000,"19990715",1,"west","flour",4,"baking"
+"AsiaPacific",1000,"19990715",1,"west","spinach",2,"produce"
+"AsiaPacific",1001,"20100715",1,"west","milk",1,"dairy"
+"AsiaPacific",1001,"20100715",1,"west","butter",2,"dairy"
+"AsiaPacific",1001,"20100715",1,"west","eggs",3,"dairy"
+"AsiaPacific",1002,"20100715",1,"west","milk",1,"dairy"
+"AsiaPacific",1002,"20100715",1,"west","butter",2,"dairy"
+"AsiaPacific",1002,"20100715",1,"west","spinach",3,"produce"
+"AsiaPacific",1500,"20100715",3,"west","butter",2,"dairy"
+"AsiaPacific",1500,"20100715",3,"west","eggs",3,"dairy"
+"AsiaPacific",1500,"20100715",3,"west","flour",4,"baking"
+"LatinAmerica",999,"20100715",1,"west","milk",1,"dairy"
+"LatinAmerica",999,"20100715",1,"west","butter",2,"dairy"
+"LatinAmerica",999,"20100715",1,"west","eggs",3,"dairy"
+"LatinAmerica",999,"19990715",1,"west","flour",4,"baking"
+"LatinAmerica",999,"19990715",1,"west","spinach",4,"produce"
+"LatinAmerica",1000,"20100715",1,"west","milk",1,"dairy"
+"LatinAmerica",1000,"20100715",1,"west","eggs",3,"dairy"
+"LatinAmerica",1000,"19990715",1,"west","flour",4,"baking"
+"LatinAmerica",1000,"19990715",1,"west","spinach",2,"produce"
+"LatinAmerica",1001,"20100715",1,"west","milk",1,"dairy"
+"LatinAmerica",1001,"20100715",1,"west","butter",2,"dairy"
+"LatinAmerica",1001,"20100715",1,"west","eggs",3,"dairy"
+"LatinAmerica",1002,"20100715",1,"west","milk",1,"dairy"
+"LatinAmerica",1002,"20100715",1,"west","butter",2,"dairy"
+"LatinAmerica",1002,"20100715",1,"west","spinach",3,"produce"
+"LatinAmerica",1500,"20100715",3,"west","butter",2,"dairy"
+"LatinAmerica",1500,"20100715",3,"west","eggs",3,"dairy"
+"LatinAmerica",1500,"20100715",3,"west","flour",4,"baking"

teradataml/data/url_data.csv

@@ -1,9 +1,10 @@
-"id","urls","part"
-0,"http://example.com:8080/path","FILE"
-1,"ftp://example.net:21/path","PATH"
-2,"https://example.net/path4/path5/path6?query4=value4#fragment3","REF"
-3,"https://www.facebook.com","HOST"
-4,"https://teracloud-pod-services-pod-account-service.dummyvalue.production.pods.teracloud.ninja/v1/accounts/acc-dummyvalue/user-environment-service/api/v1/","QUERY"
-5,"http://pg.example.ml/path150#fragment90","AUTHORITY"
-6,"smtp://user:password@smtp.example.com:21/file.txt","USERINFO"
-7,"https://www.google.com","PROTOCOL"
+"id","urls","part","query_key"
+0,"http://example.com:8080/path","FILE","path"
+1,"ftp://example.net:21/path","PATH","path"
+2,"https://example.net/path4/path5/path6?query4=value4#fragment3","REF","fragment3"
+3,"https://www.facebook.com","HOST","facebook.com"
+4,"https://teracloud-pod-services-pod-account-service.dummyvalue.production.pods.teracloud.ninja/v1/accounts/acc-dummyvalue/user-environment-service/api/v1/","QUERY",None
+5,"http://pg.example.ml/path150#fragment90","AUTHORITY","fragment90"
+6,"smtp://user:password@smtp.example.com:21/file.txt","USERINFO","password"
+7,"https://www.google.com","PROTOCOL","google.com"
+8,"http://example.com/api?query1=value1&query2=value2","QUERY","query1"

teradataml/dataframe/copy_to.py

@@ -131,7 +131,7 @@ def copy_to_sql(df, table_name,
             
         types 
             Optional Argument.
-            Specifies required data-types for requested columns to be saved in Vantage.
+            Specifies required data types for requested columns to be saved in Teradata Vantage.
             Types: Python dictionary ({column_name1: type_value1, ... column_nameN: type_valueN})
             Default: None
             
@@ -297,10 +297,10 @@ def copy_to_sql(df, table_name,
             >>> from teradatasqlalchemy.types import *
 
             >>> df = {'emp_name': ['A1', 'A2', 'A3', 'A4'],
-                'emp_sage': [100, 200, 300, 400],
-                'emp_id': [133, 144, 155, 177],
-                'marks': [99.99, 97.32, 94.67, 91.00]
-                }
+            ...       'emp_sage': [100, 200, 300, 400],
+            ...       'emp_id': [133, 144, 155, 177],
+            ...       'marks': [99.99, 97.32, 94.67, 91.00]
+            ...    }
 
             >>> pandas_df = pd.DataFrame(df)
 
@@ -313,24 +313,35 @@ def copy_to_sql(df, table_name,
 
             c) Save a Pandas DataFrame by specifying additional parameters:
             >>> copy_to_sql(df = pandas_df, table_name = 'my_table_2', schema_name = 'alice',
-                            index = True, index_label = 'my_index_label', temporary = False,
-                            primary_index = ['emp_id'], if_exists = 'append',
-                            types = {'emp_name': VARCHAR, 'emp_sage':INTEGER,
-                                     'emp_id': BIGINT, 'marks': DECIMAL})
+            ...             index = True, index_label = 'my_index_label', temporary = False,
+            ...             primary_index = ['emp_id'], if_exists = 'append',
+            ...             types = {'emp_name': VARCHAR, 'emp_sage':INTEGER,
+            ...                      'emp_id': BIGINT, 'marks': DECIMAL})
 
             d) Saving with additional parameters as a SET table
             >>> copy_to_sql(df = pandas_df, table_name = 'my_table_3', schema_name = 'alice',
-                            index = True, index_label = 'my_index_label', temporary = False,
-                            primary_index = ['emp_id'], if_exists = 'append',
-                            types = {'emp_name': VARCHAR, 'emp_sage':INTEGER,
-                                     'emp_id': BIGINT, 'marks': DECIMAL},
-                            set_table=True)
+            ...             index = True, index_label = 'my_index_label', temporary = False,
+            ...             primary_index = ['emp_id'], if_exists = 'append',
+            ...             types = {'emp_name': VARCHAR, 'emp_sage':INTEGER,
+            ...                       'emp_id': BIGINT, 'marks': DECIMAL},
+            ...             set_table=True)
 
             e) Saving levels in index of type MultiIndex
             >>> pandas_df = pandas_df.set_index(['emp_id', 'emp_name'])
             >>> copy_to_sql(df = pandas_df, table_name = 'my_table_4', schema_name = 'alice',
-                            index = True, index_label = ['index1', 'index2'], temporary = False,
-                            primary_index = ['index1'], if_exists = 'replace')
+            ...             index = True, index_label = ['index1', 'index2'], temporary = False,
+            ...             primary_index = ['index1'], if_exists = 'replace')
+            
+            f) Save a Pandas DataFrame with VECTOR datatype:
+            >>> import pandas as pd
+            >>> VECTOR_data = {
+            ...        'id': [10, 11, 12, 13],
+            ...        'array_col': ['1,1', '2,2', '3,3', '4,4']
+            ...        }
+            >>> df = pd.DataFrame(VECTOR_data)
+
+            >>> from teradatasqlalchemy import VECTOR
+            >>> copy_to_sql(df=df, table_name='my_vector_table', types={'array_col': VECTOR})
 
         2. Saving a teradataml DataFrame:
 
@@ -358,13 +369,13 @@ def copy_to_sql(df, table_name,
 
             d) Save a teradataml DataFrame by using copy_to_sql with additional parameters:
             >>> copy_to_sql(df = df2, table_name = 'my_tdml_table_3', schema_name = 'alice',
-                            temporary = False, primary_index = None, if_exists = 'append',
-                            types = {'masters': VARCHAR, 'gpa':INTEGER})
+            ...             temporary = False, primary_index = None, if_exists = 'append',
+            ...             types = {'masters': VARCHAR, 'gpa':INTEGER})
 
             e) Saving as a SET table
             >>> copy_to_sql(df = df2, table_name = 'my_tdml_set_table', schema_name = 'alice',
-                            temporary = False, primary_index = ['gpa'], if_exists = 'append',
-                            types = {'masters': VARCHAR, 'gpa':INTEGER}, set_table = True)
+            ...             temporary = False, primary_index = ['gpa'], if_exists = 'append',
+            ...             types = {'masters': VARCHAR, 'gpa':INTEGER}, set_table = True)
 
         3. Saving a teradataml DataFrame as a PTI table:
 
@@ -377,19 +388,19 @@ def copy_to_sql(df, table_name,
 
             a) Using copy_to_sql
             >>> copy_to_sql(df3, "test_copyto_pti",
-                            timecode_column='clicktime',
-                            columns_list='event')
+            ...             timecode_column='clicktime',
+            ...             columns_list='event')
 
             b) Alternatively, using DataFrame.to_sql
             >>> df3.to_sql(table_name = "test_copyto_pti_1",
-                          timecode_column='clicktime',
-                          columns_list='event')
+            ...            timecode_column='clicktime',
+            ...            columns_list='event')
 
             c) Saving as a SET table
             >>> copy_to_sql(df3, "test_copyto_pti_2",
-                            timecode_column='clicktime',
-                            columns_list='event',
-                            set_table=True)
+            ...             timecode_column='clicktime',
+            ...             columns_list='event',
+            ...             set_table=True)
 
     """
     # Deriving global connection using get_connection().

teradataml/dataframe/data_transfer.py

@@ -690,77 +690,77 @@ def read_csv(filepath,
         #            while doing so catch all errors and warnings as well as store those in the table.
         >>> types = OrderedDict(id=BIGINT, fname=VARCHAR, lname=VARCHAR, marks=FLOAT)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_table1', types=types,
-                     save_errors=True, catch_errors_warnings=True)
+        ...          table_name='my_first_table1', types=types,
+        ...          save_errors=True, catch_errors_warnings=True)
 
         # Example 3: Load the data from CSV file into a table using fastload CSV protocol.
         #            If table exists, then replace the same. Catch all errors and warnings as well as
         #            store those in the table.
         >>> types = OrderedDict(id=BIGINT, fname=VARCHAR, lname=VARCHAR, marks=FLOAT)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_table',
-                     types=types, if_exists='replace',
-                     save_errors=True, catch_errors_warnings=True)
+        ...          table_name='my_first_table',
+        ...          types=types, if_exists='replace',
+        ...          save_errors=True, catch_errors_warnings=True)
 
         # Example 4: Load the data from CSV file into a table using fastload CSV protocol.
         #            If table exists in specified schema, then append the same. Catch all
         #            errors and warnings as well as store those in the table.
         >>> types = OrderedDict(id=BIGINT, fname=VARCHAR, lname=VARCHAR, marks=FLOAT)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_table',
-                     types=types, if_exists='fail',
-                     save_errors=True, catch_errors_warnings=True)
+        ...          table_name='my_first_table',
+        ...          types=types, if_exists='fail',
+        ...          save_errors=True, catch_errors_warnings=True)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_table',
-                     if_exists='append',
-                     save_errors=True, catch_errors_warnings=True)
+        ...          table_name='my_first_table',
+        ...          if_exists='append',
+        ...          save_errors=True, catch_errors_warnings=True)
 
         # Example 5: Load the data from CSV file into a SET table using fastload CSV protocol.
         #            Catch all errors and warnings as well as store those in the table.
         >>> types = OrderedDict(id=BIGINT, fname=VARCHAR, lname=VARCHAR, marks=FLOAT)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_table',
-                     types=types, if_exists='replace',
-                     set_table=True, primary_index='id',
-                     save_errors=True, catch_errors_warnings=True)
+        ...          table_name='my_first_table',
+        ...          types=types, if_exists='replace',
+        ...          set_table=True, primary_index='id',
+        ...          save_errors=True, catch_errors_warnings=True)
 
         # Example 6: Load the data from CSV file into a temporary table without fastloadCSV protocol.
         #            If table exists, then append to the same.
         >>> types = OrderedDict(id=BIGINT, fname=VARCHAR, lname=VARCHAR, marks=FLOAT)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_table',
-                     types=types, if_exists='replace',
-                     temporary=True)
+        ...          table_name='my_first_table',
+        ...          types=types, if_exists='replace',
+        ...          temporary=True)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_table',
-                     if_exists='append',
-                     temporary=True)
+        ...          table_name='my_first_table',
+        ...          if_exists='append',
+        ...          temporary=True)
 
         # Example 7: Load the data from CSV file with DATE and TIMESTAMP columns into
         #            a table without Fastload protocol. If table exists in specified
         #            schema, then append to the table.
         >>> types = OrderedDict(id=BIGINT, fname=VARCHAR, lname=VARCHAR, marks=FLOAT,
-                     admission_date=DATE, admission_time=TIMESTAMP)
+        ...                     admission_date=DATE, admission_time=TIMESTAMP)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_table',
-                     types=types, if_exists='fail',
-                     use_fastload=False)
+        ...          table_name='my_first_table',
+        ...          types=types, if_exists='fail',
+        ...          use_fastload=False)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_table',
-                     if_exists='append',
-                     use_fastload=False)
+        ...          table_name='my_first_table',
+        ...          if_exists='append',
+        ...          use_fastload=False)
 
         # Example 8: Load the data from CSV file with TIMESTAMP columns into
         #            a PTI table. If specified table exists then append to the table,
         #            otherwise creates new table.
         >>> types = OrderedDict(partition_id=INTEGER, adid=INTEGER, productid=INTEGER,
-                                event=VARCHAR, clicktime=TIMESTAMP)
+        ...                     event=VARCHAR, clicktime=TIMESTAMP)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_read_csv_pti_table',
-                     types=types, if_exists='append',
-                     timecode_column='clicktime',
-                     columns_list='event',
-                     use_fastload=False)
+        ...          table_name='my_first_read_csv_pti_table',
+        ...          types=types, if_exists='append',
+        ...          timecode_column='clicktime',
+        ...          columns_list='event',
+        ...          use_fastload=False)
 
         # Example 9: Load the data from CSV file with TIMESTAMP columns into
         #            a SET PTI table. If specified table exists then append to the table,
@@ -768,11 +768,11 @@ def read_csv(filepath,
         >>> types = OrderedDict(partition_id=INTEGER, adid=INTEGER, productid=INTEGER,
                                 event=VARCHAR, clicktime=TIMESTAMP)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_read_csv_pti_table',
-                     types=types, if_exists='append',
-                     timecode_column='clicktime',
-                     columns_list='event',
-                     set_table=True)
+        ...          table_name='my_first_read_csv_pti_table',
+        ...          types=types, if_exists='append',
+        ...          timecode_column='clicktime',
+        ...          columns_list='event',
+        ...          set_table=True)
 
         # Example 10: Load the data from CSV file with TIMESTAMP columns into
         #            a temporary PTI table. If specified table exists then append to the table,
@@ -780,11 +780,11 @@ def read_csv(filepath,
         >>> types = OrderedDict(partition_id=INTEGER, adid=INTEGER, productid=INTEGER,
                                 event=VARCHAR, clicktime=TIMESTAMP)
         >>> read_csv(filepath='test_file.csv',
-                     table_name='my_first_read_csv_pti_table',
-                     types=types, if_exists='append',
-                     timecode_column='clicktime',
-                     columns_list='event',
-                     temporary=True)
+        ...          table_name='my_first_read_csv_pti_table',
+        ...          types=types, if_exists='append',
+        ...          timecode_column='clicktime',
+        ...          columns_list='event',
+        ...          temporary=True)
 
         # Example 11: Load the data from CSV file into Vantage table by opening specified
         #             number of Teradata data transfer sesions.
@@ -796,8 +796,24 @@ def read_csv(filepath,
         #             through primary_index argument.
         >>> types = OrderedDict(id=BIGINT, fname=VARCHAR, lname=VARCHAR, marks=FLOAT)
         >>> read_csv(filepath='test_file.csv', table_name='my_first_table_with_primary_index',
-                    types=types, primary_index = ['fname'])
+        ...          types=types, primary_index = ['fname'])
+
+        # Example 13: Load the data from CSV file into VECTOR datatype in Vantage table.
+        >>> from teradatasqlalchemy import VECTOR
+        >>> from pathlib import Path
+        >>> types = OrderedDict(id=BIGINT, array_col=VECTOR)
+
+        # Get the absolute path of the teradataml module
+        >>> import teradataml
+        >>> base_path = Path(teradataml.__path__[0])
+
+        # Append the relative path to the CSV file
+        >>> csv_path = os.path.join(base_path, "data", "hnsw_alter_data.csv")
 
+        >>> read_csv(filepath=csv_path, 
+        ...          table_name='my_first_table_with_vector',
+        ...          types=types,
+        ...          use_fastload=False)
     """
     # Deriving global connection using context.get_context()
     con = get_context()