cleancore 0.1.0__tar.gz

cleancore-0.1.0/LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2025 [Sidra Saqlain]
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

cleancore-0.1.0/PKG-INFO

@@ -0,0 +1,30 @@
+Metadata-Version: 2.4
+Name: cleancore
+Version: 0.1.0
+Summary: Dependency-free data transformation audit framework
+Author-email: Sidra <sidrasaqlain11@gmail.com>
+License: MIT
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# CleanCore
+
+CleanCore is a **dependency-free data transformation audit framework**.
+
+Unlike data profilers, CleanCore tracks:
+- What changed
+- Which rows were affected
+- Before / after values
+- Why it changed (business rule)
+- Compliance-ready audit trail
+
+## Example
+
+```python
+from cleancore import CleanEngine, print_audit_report
+
+engine = CleanEngine(df)
+cleaned_df, audit_log = engine.run()
+print_audit_report(audit_log)

cleancore-0.1.0/README.md

@@ -0,0 +1,19 @@
+# CleanCore
+
+CleanCore is a **dependency-free data transformation audit framework**.
+
+Unlike data profilers, CleanCore tracks:
+- What changed
+- Which rows were affected
+- Before / after values
+- Why it changed (business rule)
+- Compliance-ready audit trail
+
+## Example
+
+```python
+from cleancore import CleanEngine, print_audit_report
+
+engine = CleanEngine(df)
+cleaned_df, audit_log = engine.run()
+print_audit_report(audit_log)

cleancore-0.1.0/pyproject.toml

@@ -0,0 +1,16 @@
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cleancore"
+version = "0.1.0"
+description = "Dependency-free data transformation audit framework"
+authors = [
+    { name = "Sidra", email = "sidrasaqlain11@gmail.com" }
+]
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.8"
+
+dependencies = []

cleancore-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

cleancore-0.1.0/setup.py

@@ -0,0 +1,8 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="cleancore",
+    version="0.1.0",
+    package_dir={"": "src"},
+    packages=find_packages(where="src"),
+)

cleancore-0.1.0/src/cleancore/__init__.py

@@ -0,0 +1,2 @@
+from .engine import CleanEngine
+from .report import print_audit_report

cleancore-0.1.0/src/cleancore/audit.py

@@ -0,0 +1,24 @@
+class AuditEvent:
+    def __init__(
+        self,
+        audit_id,
+        timestamp,
+        transformation,
+        problem,
+        solution,
+        rule_id,
+        affected_rows,
+        before_hash,
+        after_hash,
+        status
+    ):
+        self.audit_id = audit_id
+        self.timestamp = timestamp
+        self.transformation = transformation
+        self.problem = problem
+        self.solution = solution
+        self.rule_id = rule_id
+        self.affected_rows = affected_rows
+        self.before_hash = before_hash
+        self.after_hash = after_hash
+        self.status = status

cleancore-0.1.0/src/cleancore/engine.py

@@ -0,0 +1,70 @@
+from datetime import datetime
+from .audit import AuditEvent
+from .transform import dataframe_hash
+
+class CleanEngine:
+    def __init__(self, df, id_column="CustomerID"):
+        self.df = df
+        self.id_column = id_column
+        self.audit_log = []
+        self.audit_id = "AUD20241219001"
+
+    def run(self):
+        self._impute_missing_age()
+        self._detect_constant_salary()
+        return self.df, self.audit_log
+
+    def _impute_missing_age(self):
+        if self.df["Age"].isna().sum() == 0:
+            return
+
+        before_hash = dataframe_hash(self.df)
+        median_age = self.df["Age"].median()
+
+        affected = []
+
+        for idx, row in self.df[self.df["Age"].isna()].iterrows():
+            affected.append({
+                "row_index": int(idx),
+                "customer_id": row[self.id_column],
+                "column": "Age",
+                "before": None,
+                "after": median_age
+            })
+            self.df.at[idx, "Age"] = median_age
+
+        after_hash = dataframe_hash(self.df)
+
+        event = AuditEvent(
+            audit_id=self.audit_id,
+            timestamp=datetime.utcnow().isoformat(),
+            transformation="Missing values imputation",
+            problem=f"Age has missing values ({len(affected)} rows)",
+            solution=f"Filled with median ({median_age})",
+            rule_id="GDPR_COMPLIANT_IMPUTATION_v2",
+            affected_rows=affected,
+            before_hash=before_hash,
+            after_hash=after_hash,
+            status="AUTO_FIXED"
+        )
+
+        self.audit_log.append(event)
+
+    def _detect_constant_salary(self):
+        if self.df["Salary"].std() != 0:
+            return
+
+        event = AuditEvent(
+            audit_id=self.audit_id,
+            timestamp=datetime.utcnow().isoformat(),
+            transformation="Constant column detection",
+            problem="Salary has zero variance",
+            solution="Flagged for manual review",
+            rule_id="FINANCE_RULE_001",
+            affected_rows=[],
+            before_hash=dataframe_hash(self.df),
+            after_hash=dataframe_hash(self.df),
+            status="PENDING_REVIEW"
+        )
+
+        self.audit_log.append(event)

cleancore-0.1.0/src/cleancore/report.py

@@ -0,0 +1,44 @@
+def print_audit_report(audit_log):
+    if not audit_log:
+        print("No transformations applied.")
+        return
+
+    audit_id = audit_log[0].audit_id
+
+    print(f"\nAUDIT TRAIL #{audit_id}")
+    print("=" * 40)
+
+    for i, event in enumerate(audit_log, 1):
+        print(f"\nTRANSFORMATION {i}: {event.transformation}")
+        print(f"• Problem: {event.problem}")
+        print(f"• Solution: {event.solution}")
+        print(f"• Business Rule: {event.rule_id}")
+
+        if event.affected_rows:
+            print("• Affected Records:")
+            for r in event.affected_rows:
+                print(
+                    f"   - Row {r['row_index']} "
+                    f"(Customer: {r['customer_id']}): "
+                    f"{r['before']} → {r['after']}"
+                )
+
+        print(
+            f"• Validation Hash: "
+            f"sha256:{event.before_hash[:6]} → sha256:{event.after_hash[:6]}"
+        )
+
+        if event.status == "AUTO_FIXED":
+            print("• Status: Auto-fixed")
+        else:
+            print("• Status: Pending review")
+
+    print("\nSUMMARY:")
+    total = len(audit_log)
+    auto_fixed = sum(e.status == "AUTO_FIXED" for e in audit_log)
+    pending = sum(e.status == "PENDING_REVIEW" for e in audit_log)
+
+    print(f"• Total problems: {total}")
+    print(f"• Auto-fixed: {auto_fixed}")
+    print(f"• Manual review: {pending}")
+    print(f"• Audit ID: {audit_id} (save for compliance)")

cleancore-0.1.0/src/cleancore/rules.py

@@ -0,0 +1,10 @@
+RULES = {
+    "GDPR_COMPLIANT_IMPUTATION_v2": {
+        "description": "Fill missing values using median",
+        "owner": "Data Protection Office"
+    },
+    "FINANCE_RULE_001": {
+        "description": "Constant salary requires HR approval",
+        "owner": "Finance Department"
+    }
+}

cleancore-0.1.0/src/cleancore/transform.py

@@ -0,0 +1,8 @@
+import hashlib
+
+def dataframe_hash(df):
+    """
+    Deterministic hash of dataframe content (stdlib only)
+    """
+    raw = df.to_csv(index=True).encode("utf-8")
+    return hashlib.sha256(raw).hexdigest()

cleancore-0.1.0/src/cleancore.egg-info/PKG-INFO

@@ -0,0 +1,30 @@
+Metadata-Version: 2.4
+Name: cleancore
+Version: 0.1.0
+Summary: Dependency-free data transformation audit framework
+Author-email: Sidra <sidrasaqlain11@gmail.com>
+License: MIT
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# CleanCore
+
+CleanCore is a **dependency-free data transformation audit framework**.
+
+Unlike data profilers, CleanCore tracks:
+- What changed
+- Which rows were affected
+- Before / after values
+- Why it changed (business rule)
+- Compliance-ready audit trail
+
+## Example
+
+```python
+from cleancore import CleanEngine, print_audit_report
+
+engine = CleanEngine(df)
+cleaned_df, audit_log = engine.run()
+print_audit_report(audit_log)

cleancore-0.1.0/src/cleancore.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+LICENSE
+README.md
+pyproject.toml
+setup.py
+src/cleancore/__init__.py
+src/cleancore/audit.py
+src/cleancore/engine.py
+src/cleancore/report.py
+src/cleancore/rules.py
+src/cleancore/transform.py
+src/cleancore.egg-info/PKG-INFO
+src/cleancore.egg-info/SOURCES.txt
+src/cleancore.egg-info/dependency_links.txt
+src/cleancore.egg-info/top_level.txt

cleancore-0.1.0/src/cleancore.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

cleancore-0.1.0/src/cleancore.egg-info/top_level.txt

@@ -0,0 +1 @@
+cleancore