deepcsv 0.1.0__tar.gz → 0.3.0__tar.gz

deepcsv-0.3.0/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: deepcsv
+Version: 0.3.0
+Summary: Automatically walks through folders and subfolders, finds all CSV and XLSX files, detects and fixes data issues, and saves the results as Parquet files while keeping the exact same folder structure.
+Author: Abdullah Bakr
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: pyarrow
+Dynamic: author
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# deepcsv
+
+A Python library that automatically walks through folders and subfolders, finds all CSV and XLSX files, detects and fixes data issues, and saves the results as Parquet files while keeping the exact same folder structure.
+
+## Installation
+```bash
+pip install deepcsv
+```
+
+## What it does
+
+- Walks through all folders and subfolders automatically
+- Finds every CSV and XLSX file
+- Detects columns that contain list strings like `"['item1', 'item2']"` and converts them into real Python arrays for faster performance
+- Detects columns with mixed data types and tries to fix them automatically
+- Warns you when a column has mixed types so you know what was changed
+- Saves the results as Parquet files to preserve the converted data types
+
+> **Why Parquet?**
+> CSV files cannot store arrays or preserve data types. Parquet solves this by keeping the exact types after conversion.
+
+> **Why arrays instead of Python lists?**
+> Arrays are significantly faster for numerical operations and machine learning workflows.
+
+## Functions
+
+### `ConvertListStrToList(file_path)`
+
+Reads a CSV file, converts list strings to arrays, fixes mixed-type columns, and returns a clean DataFrame.
+```python
+import deepcsv
+
+df = deepcsv.ConvertListStrToList("path/to/file.csv")
+```
+
+### `ReadAllCSVData(path)`
+
+Walks through all folders and subfolders, applies `ConvertListStrToList` on every CSV and XLSX file, and saves the results as Parquet files in a new folder called `All CSV Data is Converted Here`.
+```python
+import deepcsv
+
+deepcsv.ReadAllCSVData("path/to/folder")
+```
+
+## Notes
+
+- Only files that contain list string columns are saved as Parquet
+- Mixed-type columns are converted to float automatically when possible
+- Skips NaN values without breaking
+- Requires `pyarrow` for Parquet support
+
+## Requirements
+
+- Python >= 3.7
+- pandas
+- pyarrow

deepcsv-0.3.0/README.md

@@ -0,0 +1,56 @@
+# deepcsv
+
+A Python library that automatically walks through folders and subfolders, finds all CSV and XLSX files, detects and fixes data issues, and saves the results as Parquet files while keeping the exact same folder structure.
+
+## Installation
+```bash
+pip install deepcsv
+```
+
+## What it does
+
+- Walks through all folders and subfolders automatically
+- Finds every CSV and XLSX file
+- Detects columns that contain list strings like `"['item1', 'item2']"` and converts them into real Python arrays for faster performance
+- Detects columns with mixed data types and tries to fix them automatically
+- Warns you when a column has mixed types so you know what was changed
+- Saves the results as Parquet files to preserve the converted data types
+
+> **Why Parquet?**
+> CSV files cannot store arrays or preserve data types. Parquet solves this by keeping the exact types after conversion.
+
+> **Why arrays instead of Python lists?**
+> Arrays are significantly faster for numerical operations and machine learning workflows.
+
+## Functions
+
+### `ConvertListStrToList(file_path)`
+
+Reads a CSV file, converts list strings to arrays, fixes mixed-type columns, and returns a clean DataFrame.
+```python
+import deepcsv
+
+df = deepcsv.ConvertListStrToList("path/to/file.csv")
+```
+
+### `ReadAllCSVData(path)`
+
+Walks through all folders and subfolders, applies `ConvertListStrToList` on every CSV and XLSX file, and saves the results as Parquet files in a new folder called `All CSV Data is Converted Here`.
+```python
+import deepcsv
+
+deepcsv.ReadAllCSVData("path/to/folder")
+```
+
+## Notes
+
+- Only files that contain list string columns are saved as Parquet
+- Mixed-type columns are converted to float automatically when possible
+- Skips NaN values without breaking
+- Requires `pyarrow` for Parquet support
+
+## Requirements
+
+- Python >= 3.7
+- pandas
+- pyarrow

deepcsv-0.3.0/deepcsv/deepcsv.py

@@ -0,0 +1,76 @@
+import pyarrow
+import os
+import warnings
+import numpy as np
+import pandas as pd
+from ast import literal_eval
+warnings.filterwarnings("ignore")
+
+def ConvertListStrToList(File_Path):
+
+    data = pd.read_csv(File_Path)
+    for ColName in data.columns:
+        
+        First_Value = data[ColName].iloc[0]
+
+        if len(data[ColName].apply(type).unique()) >= 2:
+
+
+            sample = (data[data[ColName].apply(type) == str][ColName].head(2)).values
+
+            if len(sample) > 0 and isinstance(sample[0],str) and sample[0][0].strip().isnumeric():
+
+                print(f"WARNING:\nThis Dataset Name ({File_Path.split("\\")[-1]}) Found {len(data[ColName].apply(type).unique())} Mixed DataType  in a column called ({ColName})\nPath : {File_Path}")
+                print(f"System : This column have These types: {data[ColName].apply(type).unique()}")
+                print(f"System : Trying to fix the column as a Float to be have only one datatype...")
+
+                data[ColName] = pd.to_numeric(data[ColName], errors='coerce')
+                print("System : Done!")
+
+        elif isinstance(First_Value , str) and First_Value.strip().startswith("["):
+            
+            data[f"{ColName.capitalize()}List"] = data[ColName].apply(lambda x : literal_eval(x) if pd.notna(x) else np.nan)
+            data.drop(ColName,inplace=True,axis=1)
+
+    return data
+
+
+def ReadAllCSVData(WorkDirectoryPath):
+
+    base_output = os.path.join(WorkDirectoryPath, "All CSV Data is Converted Here")
+    all_folders = [WorkDirectoryPath]
+    
+    os.makedirs(base_output,exist_ok=True)
+    
+    while True:
+
+        if all_folders:
+
+            Curr_Path = all_folders.pop(0)
+
+            for item_name in os.listdir(Curr_Path):
+                
+                Sub_Item_Path = os.path.join(Curr_Path,item_name)
+                
+                if os.path.isfile(Sub_Item_Path) and (Sub_Item_Path.endswith(".csv") or Sub_Item_Path.endswith(".xlsx")):
+                    
+                        
+
+                    df_converted = ConvertListStrToList(Sub_Item_Path)
+                    df_converted.reset_index(drop=True,inplace=True)
+
+                    rel_path = os.path.relpath(Sub_Item_Path, WorkDirectoryPath)
+                    output = os.path.join(base_output,rel_path)
+                    if "List" in df_converted.columns[-1]:
+                        print(Sub_Item_Path)
+                        os.makedirs(os.path.dirname(output),exist_ok=True)
+                        df_converted.to_parquet(output.replace(".csv", ".parquet"))
+
+                    print("-"*50)
+
+                elif os.path.isdir(Sub_Item_Path):
+
+                    all_folders.append(Sub_Item_Path)
+
+        else:
+            break

deepcsv-0.3.0/deepcsv.egg-info/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: deepcsv
+Version: 0.3.0
+Summary: Automatically walks through folders and subfolders, finds all CSV and XLSX files, detects and fixes data issues, and saves the results as Parquet files while keeping the exact same folder structure.
+Author: Abdullah Bakr
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: pyarrow
+Dynamic: author
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# deepcsv
+
+A Python library that automatically walks through folders and subfolders, finds all CSV and XLSX files, detects and fixes data issues, and saves the results as Parquet files while keeping the exact same folder structure.
+
+## Installation
+```bash
+pip install deepcsv
+```
+
+## What it does
+
+- Walks through all folders and subfolders automatically
+- Finds every CSV and XLSX file
+- Detects columns that contain list strings like `"['item1', 'item2']"` and converts them into real Python arrays for faster performance
+- Detects columns with mixed data types and tries to fix them automatically
+- Warns you when a column has mixed types so you know what was changed
+- Saves the results as Parquet files to preserve the converted data types
+
+> **Why Parquet?**
+> CSV files cannot store arrays or preserve data types. Parquet solves this by keeping the exact types after conversion.
+
+> **Why arrays instead of Python lists?**
+> Arrays are significantly faster for numerical operations and machine learning workflows.
+
+## Functions
+
+### `ConvertListStrToList(file_path)`
+
+Reads a CSV file, converts list strings to arrays, fixes mixed-type columns, and returns a clean DataFrame.
+```python
+import deepcsv
+
+df = deepcsv.ConvertListStrToList("path/to/file.csv")
+```
+
+### `ReadAllCSVData(path)`
+
+Walks through all folders and subfolders, applies `ConvertListStrToList` on every CSV and XLSX file, and saves the results as Parquet files in a new folder called `All CSV Data is Converted Here`.
+```python
+import deepcsv
+
+deepcsv.ReadAllCSVData("path/to/folder")
+```
+
+## Notes
+
+- Only files that contain list string columns are saved as Parquet
+- Mixed-type columns are converted to float automatically when possible
+- Skips NaN values without breaking
+- Requires `pyarrow` for Parquet support
+
+## Requirements
+
+- Python >= 3.7
+- pandas
+- pyarrow

{deepcsv-0.1.0 → deepcsv-0.3.0}/deepcsv.egg-info/SOURCES.txt

@@ -1,4 +1,5 @@
 LICENSE
+README.md
 setup.py
 deepcsv/__init__.py
 deepcsv/deepcsv.py

deepcsv-0.3.0/deepcsv.egg-info/requires.txt

@@ -0,0 +1,2 @@
+pandas
+pyarrow

deepcsv-0.3.0/setup.py

@@ -0,0 +1,13 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="deepcsv",
+    version="0.3.0",
+    author="Abdullah Bakr",
+    description="Automatically walks through folders and subfolders, finds all CSV and XLSX files, detects and fixes data issues, and saves the results as Parquet files while keeping the exact same folder structure.",
+    long_description=open("README.md").read(),
+    long_description_content_type="text/markdown",
+    packages=find_packages(),
+    install_requires=["pandas","pyarrow"],
+    python_requires=">=3.7",
+)

deepcsv-0.1.0/PKG-INFO

@@ -1,13 +0,0 @@
-Metadata-Version: 2.4
-Name: deepcsv
-Version: 0.1.0
-Summary: Automatically walks folders and converts list strings to lists in CSV/XLSX files
-Author: Abdullah Bakr
-Requires-Python: >=3.7
-License-File: LICENSE
-Requires-Dist: pandas
-Dynamic: author
-Dynamic: license-file
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary

deepcsv-0.1.0/deepcsv/deepcsv.py

@@ -1,49 +0,0 @@
-import os
-import pandas as pd
-from ast import literal_eval
-
-def ConvertListStrToList(data):
-    Data_Col = data.columns
-    for ColName in Data_Col:
-        if type(data[ColName][0]) == str and data[ColName][0].startswith("["):
-            data[f"{ColName.capitalize()}List"] = data[ColName].apply(lambda x : literal_eval(x) if pd.notna(x) else x )
-            data.drop(ColName,inplace=True,axis=1)
-    
-    return data
-
-
-def ReadAllCSVData(WorkDirectoryPath):
-
-    base_output = os.path.join(WorkDirectoryPath, "All CSV Data is Converted Here")
-    all_folders = [WorkDirectoryPath]
-    
-    os.makedirs(base_output,exist_ok=True)
-    
-    while True:
-
-        if all_folders:
-
-            Curr_Path = all_folders.pop(0)
-
-            for item_name in os.listdir(Curr_Path):
-                
-                Sub_Item_Path = os.path.join(Curr_Path,item_name)
-                
-                if os.path.isfile(Sub_Item_Path) and (Sub_Item_Path.endswith(".csv") or Sub_Item_Path.endswith(".xlsx")):
-                    print(Sub_Item_Path)
-                    df = pd.read_csv(Sub_Item_Path)
-                    df_converted = ConvertListStrToList(df)
-
-                    rel_path = os.path.relpath(Sub_Item_Path, WorkDirectoryPath)
-                    output = os.path.join(base_output,rel_path)
-                    os.makedirs(os.path.dirname(output),exist_ok=True)
-
-                    df_converted.to_csv(output)
-
-
-                elif os.path.isdir(Sub_Item_Path):
-
-                    all_folders.append(Sub_Item_Path)
-
-        else:
-            break

deepcsv-0.1.0/deepcsv.egg-info/PKG-INFO

@@ -1,13 +0,0 @@
-Metadata-Version: 2.4
-Name: deepcsv
-Version: 0.1.0
-Summary: Automatically walks folders and converts list strings to lists in CSV/XLSX files
-Author: Abdullah Bakr
-Requires-Python: >=3.7
-License-File: LICENSE
-Requires-Dist: pandas
-Dynamic: author
-Dynamic: license-file
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary

deepcsv-0.1.0/deepcsv.egg-info/requires.txt

@@ -1 +0,0 @@
-pandas

deepcsv-0.1.0/setup.py

@@ -1,11 +0,0 @@
-from setuptools import setup, find_packages
-
-setup(
-    name="deepcsv",
-    version="0.1.0",
-    author="Abdullah Bakr",
-    description="Automatically walks folders and converts list strings to lists in CSV/XLSX files",
-    packages=find_packages(),
-    install_requires=["pandas"],
-    python_requires=">=3.7",
-)