fslink 0.1.0__py3-none-any.whl

fslink/__initi__.py

@@ -0,0 +1 @@
+from .core import say_hello

fslink/core.py

@@ -0,0 +1,30 @@
+def say_hello(name: str) -> str:
+    return f"Hello, {name}! Welcome to my package."
+
+# my_package/data_processor.py
+from pyspark.sql import SparkSession
+from pyspark.sql import DataFrame
+
+def transform_data(spark: SparkSession, df: DataFrame) -> DataFrame:
+    """Accepts a DataFrame, splits and link, and returns a new DataFrame."""
+    #Find features
+    #email,address,ssn,dob,lastname,firstname,phone
+    
+    #
+    
+    
+    
+    # 1. Perform your business logic / transformations
+    cleaned_df = df.dropna(subset=["customer_id"])
+    final_df = cleaned_df.dropDuplicates(["transaction_id"])
+    
+    # 2. Return the DataFrame object back to Databricks
+    return final_df
+
+
+def clean_dataframe(spark: SparkSession, df):
+    """Safely uses Spark inside a packaged module."""
+    # Do not call spark = SparkSession.builder... on Databricks clusters.
+    # Instead, accept the active notebook session passed by the user.
+    return df.dropDuplicates().dropna()
+

fslink-0.1.0.dist-info/METADATA

@@ -0,0 +1,12 @@
+Metadata-Version: 2.4
+Name: fslink
+Version: 0.1.0
+Summary: A simple record linkage package
+Project-URL: Homepage, https://github.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file

fslink-0.1.0.dist-info/RECORD

@@ -0,0 +1,7 @@
+fslink/__initi__.py,sha256=SfV0woikYS0YSV-LqZqAQebTlELBevpYSQ_KmkjnwDU,27
+fslink/core.py,sha256=ZAY6Z34aT2FT2YO2eaKcPDHM6Yn0ka_cK5IP7YuS4p4,997
+fslink-0.1.0.dist-info/licenses/LICENSE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+fslink-0.1.0.dist-info/METADATA,sha256=c-xDJbPRAHt2D04LII_pJvMkTBrfZg0pwI90oc98j0E,398
+fslink-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+fslink-0.1.0.dist-info/top_level.txt,sha256=htloryvW-rRKjveQjr7XIWIn4pW7M1cjeWf5QyGJGZU,7
+fslink-0.1.0.dist-info/RECORD,,

fslink-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

fslink-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+fslink