dbis-functional-dependencies 1.0.0__tar.gz → 1.0.2__tar.gz

{dbis_functional_dependencies-1.0.0 → dbis_functional_dependencies-1.0.2}/PKG-INFO

@@ -1,11 +1,12 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: dbis-functional-dependencies
-Version: 1.0.0
+Version: 1.0.2
 Summary: RWTH Aachen Computer Science i5/dbis assets for Lecture Datenbanken und Informationssysteme
 Author-email: DBIS i5 RWTH Aachen <dbis-vl@dbis.rwth-aachen.de>
 Project-URL: Homepage, https://git.rwth-aachen.de/i5/teaching/dbis/dbis-functional-dependencies
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.13
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -16,12 +17,12 @@ Requires-Dist: sphinx~=7.2
 Requires-Dist: sphinxcontrib-apidoc~=0.4
 Requires-Dist: functional-dependencies~=1.3
 Requires-Dist: build~=1.0
-Requires-Dist: pylodstorage~=0.4.11
 Provides-Extra: test
 Requires-Dist: black==23.12.1; extra == "test"
 Provides-Extra: build
-Requires-Dist: twine==4.*; extra == "build"
+Requires-Dist: twine==6.*; extra == "build"
 Requires-Dist: build==1.*; extra == "build"
+Dynamic: license-file
 
 # DBIS Functional Dependencies
 

{dbis_functional_dependencies-1.0.0 → dbis_functional_dependencies-1.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name="dbis-functional-dependencies"
-version='1.0.0'
+version='1.0.2'
 description="RWTH Aachen Computer Science i5/dbis assets for Lecture Datenbanken und Informationssysteme"
 
 authors = [
@@ -10,7 +10,8 @@ readme = "README.md"
 requires-python = ">=3.10"
 classifiers = [
 	"Programming Language :: Python :: 3.10",
-	"Programming Language :: Python :: 3.11"
+	"Programming Language :: Python :: 3.11",
+	"Programming Language :: Python :: 3.13"
 ]
 
 dependencies = [
@@ -21,7 +22,6 @@ dependencies = [
 	"sphinxcontrib-apidoc~=0.4",
 	"functional-dependencies~=1.3",
 	"build~=1.0",
-	"pylodstorage~=0.4.11"
 ]
 
 [project.optional-dependencies]
@@ -29,7 +29,7 @@ test = [
     "black==23.12.1"
 ]
 build = [
-    "twine==4.*",
+    "twine==6.*",
     "build==1.*"
 ]
 

dbis_functional_dependencies-1.0.2/src/dbis_functional_dependencies/fdcheck.py

@@ -0,0 +1,166 @@
+"""
+Created on 2022-06-11
+@author: wf
+"""
+import time
+from dbis_functional_dependencies.BCNF import FunctionalDependencySet
+import sqlite3
+
+
+class FDCheck:
+    """
+    check functional dependencies for a tabular dataset in list of dicts form
+    """
+
+    def __init__(self, lod: list, debug: bool = False):
+        """
+        construct me with the given list of dicts
+
+        Args:
+            lod(list): the list of dicts (table) to check
+            debug(bool): if true switch on debugging
+        """
+        self.lod = lod
+        self.debug = debug
+        self.entityInfo = None
+        self.conn = None
+
+    def createDatabase(
+        self,
+        entityName,
+        primaryKey=None,
+        executeMany=True,
+        fixNone=False,
+        fixDates=False,
+        debug=False,
+        doClose=True,
+    ):
+        """
+        create a database for my list of Records
+
+        Args:
+           entityName(string): the name of the entity type to be used as a table name
+           primaryKey(string): the name of the key / column to be used as a primary key
+           executeMany(boolean): True if executeMany mode of sqlite3 should be used
+           fixNone(boolean): fix dict entries that are undefined to have a "None" entry
+           debug(boolean): True if debug information e.g. CREATE TABLE and INSERT INTO commands should be shown
+           doClose(boolean): True if the connection should be closed
+
+        """
+        size = len(self.lod)
+        if self.debug:
+            print(
+                "%s size is %d fixNone is %r fixDates is: %r"
+                % (entityName, size, fixNone, fixDates)
+            )
+
+        self.conn = sqlite3.connect(":memory:")
+        cursor = self.conn.cursor()
+
+        # Infer schema
+        keys = self.lod[0].keys()
+        columns = []
+        for k in keys:
+            value = self.lod[0][k]
+            sql_type = (
+                "INTEGER"
+                if isinstance(value, int)
+                else "REAL"
+                if isinstance(value, float)
+                else "TEXT"
+            )
+            col_def = f"{k} {sql_type}"
+            if k == primaryKey:
+                col_def += " PRIMARY KEY"
+            columns.append(col_def)
+        create_stmt = f"CREATE TABLE {entityName} ({', '.join(columns)});"
+        if debug:
+            print(create_stmt)
+        cursor.execute(create_stmt)
+
+        # Prepare data
+        col_names = list(keys)
+        placeholders = ", ".join(["?"] * len(col_names))
+        insert_stmt = (
+            f"INSERT INTO {entityName} ({', '.join(col_names)}) VALUES ({placeholders})"
+        )
+
+        values = []
+        for row in self.lod:
+            values.append(tuple(row.get(k, None) for k in col_names))
+
+        startTime = time.time()
+        if executeMany:
+            cursor.executemany(insert_stmt, values)
+        else:
+            for v in values:
+                cursor.execute(insert_stmt, v)
+        self.conn.commit()
+
+        elapsed = max(1e-12, time.time() - startTime)
+        if self.debug:
+            print(
+                f"adding {size} {entityName} records took {elapsed:.3f} s => {size/elapsed:.0f} records/s"
+            )
+
+            cursor.execute(f"SELECT * FROM {entityName}")
+            resultList = cursor.fetchall()
+            print(
+                f"selecting {len(resultList)} {entityName} records took {elapsed:.3f} s => {len(resultList)/elapsed:.0f} records/s"
+            )
+
+        self.entityInfo = {
+            "name": entityName,
+            "typeMap": {k: type(self.lod[0][k]) for k in keys},
+            "fields": list(keys),
+        }
+
+        if doClose:
+            cursor.close()
+            self.conn.close()
+            self.conn = None
+
+        return self.entityInfo
+
+    def findFDs(self):
+        """
+        find functional dependencies
+
+        https://github.com/gustavclausen/functional-dependency-finder/blob/master/main.py
+        Return:
+            FunctionalDependencySet: the set of functional dependencies
+        """
+        if self.entityInfo is None or not self.conn:
+            raise Exception("createDatabase must be called before findFDs")
+
+        table_name = self.entityInfo["name"]
+        fields = self.entityInfo["fields"]
+
+        fds = FunctionalDependencySet()
+        for i, field in enumerate(fields):
+            attr1_var = chr(ord("A") + i)
+            fds.add_attribute(attr1_var, field)
+
+        cursor = self.conn.cursor()
+        for i, field_1 in enumerate(fields):
+            attr1_var = chr(ord("A") + i)
+            for j, field_2 in enumerate(fields):
+                if i == j:
+                    continue
+                attr2_var = chr(ord("A") + j)
+                sql = (
+                    f"SELECT {field_1}, COUNT(DISTINCT {field_2}) as c\n"
+                    f"FROM {table_name}\n"
+                    f"GROUP BY {field_1}\n"
+                    f"HAVING c > 1"
+                )
+                cursor.execute(sql)
+                hits = cursor.fetchall()
+                if self.debug:
+                    print(f"{sql.strip()}\n{hits}")
+                if not hits:
+                    fds.add_dependency(attr1_var, attr2_var)
+
+        cursor.close()
+        self.fds = fds
+        return fds

{dbis_functional_dependencies-1.0.0 → dbis_functional_dependencies-1.0.2}/src/dbis_functional_dependencies.egg-info/PKG-INFO

@@ -1,11 +1,12 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: dbis-functional-dependencies
-Version: 1.0.0
+Version: 1.0.2
 Summary: RWTH Aachen Computer Science i5/dbis assets for Lecture Datenbanken und Informationssysteme
 Author-email: DBIS i5 RWTH Aachen <dbis-vl@dbis.rwth-aachen.de>
 Project-URL: Homepage, https://git.rwth-aachen.de/i5/teaching/dbis/dbis-functional-dependencies
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.13
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -16,12 +17,12 @@ Requires-Dist: sphinx~=7.2
 Requires-Dist: sphinxcontrib-apidoc~=0.4
 Requires-Dist: functional-dependencies~=1.3
 Requires-Dist: build~=1.0
-Requires-Dist: pylodstorage~=0.4.11
 Provides-Extra: test
 Requires-Dist: black==23.12.1; extra == "test"
 Provides-Extra: build
-Requires-Dist: twine==4.*; extra == "build"
+Requires-Dist: twine==6.*; extra == "build"
 Requires-Dist: build==1.*; extra == "build"
+Dynamic: license-file
 
 # DBIS Functional Dependencies
 

{dbis_functional_dependencies-1.0.0 → dbis_functional_dependencies-1.0.2}/src/dbis_functional_dependencies.egg-info/requires.txt

@@ -5,10 +5,9 @@ sphinx~=7.2
 sphinxcontrib-apidoc~=0.4
 functional-dependencies~=1.3
 build~=1.0
-pylodstorage~=0.4.11
 
 [build]
-twine==4.*
+twine==6.*
 build==1.*
 
 [test]

{dbis_functional_dependencies-1.0.0 → dbis_functional_dependencies-1.0.2}/tests/test_fdfromdata.py

@@ -7,7 +7,6 @@ from pathlib import Path
 import json
 
 from tests.fdstest import FunctionalDependencySetTest
-from lodstorage.jsonable import JSONAble
 
 from dbis_functional_dependencies.fdcheck import FDCheck
 
@@ -33,8 +32,8 @@ class Test_FD_FromData(FunctionalDependencySetTest):
             the jsonFileNme to read from
         """
         jsonFilePath = f"{self.sampleDataPath}/{jsonFileName}"
-        jsonStr = JSONAble.readJsonFromFile(jsonFilePath)
-        lod = json.loads(jsonStr)
+        with open(jsonFilePath, "r", encoding="utf-8") as f:
+            lod = json.load(f)
         return lod
 
     def testExamples(self):
@@ -56,7 +55,7 @@ class Test_FD_FromData(FunctionalDependencySetTest):
                 print(lod)
             self.assertTrue(type(lod) is list)
             expectedLen = expected[i]["len"]
-            self.assertEquals(expectedLen, len(lod))
+            self.assertEqual(expectedLen, len(lod))
             fdCheck = FDCheck(lod, debug=True)
             entityName = example["entityName"]
             fdCheck.createDatabase(entityName, doClose=False)

dbis_functional_dependencies-1.0.0/src/dbis_functional_dependencies/fdcheck.py

@@ -1,113 +0,0 @@
-"""
-Created on 2022-06-11
-@author: wf
-"""
-import time
-from dbis_functional_dependencies.BCNF import FunctionalDependencySet
-from lodstorage.sql import SQLDB
-
-
-class FDCheck:
-    """
-    check functional dependencies for a tabular dataset in list of dicts form
-    """
-
-    def __init__(self, lod: list, debug: bool = False):
-        """
-        construct me with the given list of dicts
-
-        Args:
-            lod(list): the list of dicts (table) to check
-            debug(bool): if true switch on debugging
-        """
-        self.lod = lod
-        self.debug = debug
-        self.entityInfo = None
-
-    def createDatabase(
-        self,
-        entityName,
-        primaryKey=None,
-        executeMany=True,
-        fixNone=False,
-        fixDates=False,
-        debug=False,
-        doClose=True,
-    ):
-        """
-        create a database for my list of Records
-
-        Args:
-           entityName(string): the name of the entity type to be used as a table name
-           primaryKey(string): the name of the key / column to be used as a primary key
-           executeMany(boolean): True if executeMany mode of sqlite3 should be used
-           fixNone(boolean): fix dict entries that are undefined to have a "None" entry
-           debug(boolean): True if debug information e.g. CREATE TABLE and INSERT INTO commands should be shown
-           doClose(boolean): True if the connection should be closed
-
-        """
-        size = len(self.lod)
-        if self.debug:
-            print(
-                "%s size is %d fixNone is %r fixDates is: %r"
-                % (entityName, size, fixNone, fixDates)
-            )
-        self.sqlDB = SQLDB(debug=debug, errorDebug=True)
-        entityInfo = self.sqlDB.createTable(self.lod, entityName, primaryKey)
-        startTime = time.time()
-        self.sqlDB.store(self.lod, entityInfo, executeMany=executeMany, fixNone=fixNone)
-        elapsed = (
-            0.000000000001 if time.time() - startTime == 0 else time.time() - startTime
-        )
-        if self.debug:
-            print(
-                "adding %d %s records took %5.3f s => %5.f records/s"
-                % (size, entityName, elapsed, size / elapsed)
-            )
-        if self.debug:
-            resultList = self.sqlDB.queryAll(entityInfo, fixDates=fixDates)
-            print(
-                "selecting %d %s records took %5.3f s => %5.f records/s"
-                % (len(resultList), entityName, elapsed, len(resultList) / elapsed)
-            )
-        if doClose:
-            self.sqlDB.close()
-        self.entityInfo = entityInfo
-        return entityInfo
-
-    def findFDs(self):
-        """
-        find functional dependencies
-
-        https://github.com/gustavclausen/functional-dependency-finder/blob/master/main.py
-        Return:
-            FunctionalDependencySet: the set of functional dependencies
-        """
-        if self.entityInfo is None:
-            raise Exception("createDataBase needed to supply entityInfo")
-        fields = list(self.entityInfo.typeMap.keys())
-        table_name = self.entityInfo.name
-        fds = FunctionalDependencySet()
-        for i, field in enumerate(fields):
-            attr1_var = chr(ord("A") + i)
-            fds.add_attribute(attr1_var, field)
-        for i, field in enumerate(fields):
-            attr1_var = chr(ord("A") + i)
-            for j in range(0, len(fields)):
-                if i == j:
-                    continue
-
-                field_1 = fields[i]
-                field_2 = fields[j]
-                attr2_var = chr(ord("A") + j)
-                sql = f"SELECT {field_1}, COUNT(DISTINCT {field_2}) c FROM {table_name} GROUP BY {field_1} HAVING c > 1"
-                hits = self.sqlDB.query(sql)
-                if self.debug:
-                    print(f"{sql}\n{hits}")
-
-                if len(hits) == 0:
-                    # Functional dependency found: it's not the case that there's more than one value (field_2)
-                    # associated with field_1
-                    fds.add_dependency(attr1_var, attr2_var)
-        self.fds = fds
-        return fds