deepcsv 0.6.3__tar.gz → 0.6.4__tar.gz

deepcsv-0.6.4/CHANGELOG.md

@@ -0,0 +1,16 @@
+# Changelog
+
+---
+
+### Added
+
+- `process_file()` — Converting any columns have Numbers as strings to Numerical Values (Float)
+- `save_as` — Added function to save dataset file
+
+---
+
+### Fixes
+
+- `process_file()` — Fixed some bugs in `file_format` parameter
+
+---

{deepcsv-0.6.3/deepcsv.egg-info → deepcsv-0.6.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepcsv
-Version: 0.6.3
+Version: 0.6.4
 Summary: Automatically processes data files in directories, converts array-like strings to NumPy arrays, detects and fixes data type issues, and saves results as optimized Parquet files and MORE!
 Home-page: https://github.com/abdubakr77/deepcsv
 Author: Abdullah Bakr
@@ -35,6 +35,13 @@ Dynamic: requires-python
 Dynamic: summary
 
 # deepcsv
+
+![PyPI Downloads](https://img.shields.io/pypi/dm/deepcsv?color=blue&label=Downloads)
+![PyPI Version](https://img.shields.io/pypi/v/deepcsv?color=green&label=Version)
+![Python](https://img.shields.io/pypi/pyversions/deepcsv?color=yellow&label=Python)
+![License](https://img.shields.io/github/license/abdubakr77/deepcsv?color=orange)
+![GitHub Stars](https://img.shields.io/github/stars/abdubakr77/deepcsv?color=yellow)
+
 > *"You think you saved a list. You open it tomorrow — and it's a string."*
 
 `deepcsv` was built to solve exactly this problem.
@@ -245,18 +252,13 @@ auto_fix(data_input: Union[str, pd.DataFrame])
 
 ### Added
 
-- `process_file` — Added Doc & Examples for new params in function
-- `process_all_files` — Added Doc & Examples for new params in function
-- `process_file` & `process_all_file` — Added New parameter `to_list` to be real python list if you don't need array
-- Added `auto_fix` function for automatic data type correction in DataFrames for mixed Dtypes.
-- Added logg to `auto_fix` to track changes made to columns.
-- Added Documentation for `auto_fix` function to understand more about function.
+- `process_file()` — Converting any columns have Numbers as strings to Numerical Values (Float)
+- `save_as` — Added function to save dataset file
 
 ---
 
-### Changed
+### Fixes
 
-- `process_file()` — Changed `save_file_extension` parameter to `file_format`
-- `process_all_files()` — Changed `file_extension` parameter to `file_format`
+- `process_file()` — Fixed some bugs in `file_format` parameter
 
 ---

{deepcsv-0.6.3 → deepcsv-0.6.4}/README.md

@@ -1,4 +1,11 @@
 # deepcsv
+
+![PyPI Downloads](https://img.shields.io/pypi/dm/deepcsv?color=blue&label=Downloads)
+![PyPI Version](https://img.shields.io/pypi/v/deepcsv?color=green&label=Version)
+![Python](https://img.shields.io/pypi/pyversions/deepcsv?color=yellow&label=Python)
+![License](https://img.shields.io/github/license/abdubakr77/deepcsv?color=orange)
+![GitHub Stars](https://img.shields.io/github/stars/abdubakr77/deepcsv?color=yellow)
+
 > *"You think you saved a list. You open it tomorrow — and it's a string."*
 
 `deepcsv` was built to solve exactly this problem.

deepcsv-0.6.4/deepcsv/__init__.py

@@ -0,0 +1,31 @@
+from .deepcsv import process_all_files, process_file 
+from .utils import read_any, clean_values, auto_fix, save_as ,_validate_cols , _validate_index , _parse_operator , _validate_condition , _val_dtype
+from importlib.metadata import PackageNotFoundError, version as _version
+import requests as _requests
+
+__all__ = [
+    "process_file",
+    "process_all_files",
+    "read_any",
+    "clean_values",
+    "auto_fix",
+    "save_as"
+]
+
+
+def _check_for_updates():
+    try:
+        response = _requests.get("https://pypi.org/pypi/deepcsv/json", timeout=5)
+        latest = response.json()["info"]["version"]
+        current = _version("deepcsv")
+        if latest != current:
+            print(
+                f"DeepCSV: update available — run 'pip install -U deepcsv' ({latest})"
+            )
+    except PackageNotFoundError:
+        pass
+    except Exception:
+        pass
+
+
+_check_for_updates()

{deepcsv-0.6.3 → deepcsv-0.6.4}/deepcsv/deepcsv.py

@@ -1,6 +1,6 @@
 import pyarrow
 import pandas as pd
-from .utils import read_any, clean_values, _validate_cols, _validate_index,_parse_operator,_validate_condition,_save_as
+from deepcsv import read_any, save_as
 from typing import Union
 from ast import literal_eval
 from numpy import nan,array
@@ -9,7 +9,7 @@ from os.path import join,relpath,dirname,isfile,isdir
 from warnings import filterwarnings
 filterwarnings("ignore")
 
-def process_file(data_input: Union[str, pd.DataFrame] , file_format= str, to_list = False) -> pd.DataFrame:
+def process_file(data_input: Union[str, pd.DataFrame] , file_format: None, to_list = False) -> pd.DataFrame:
     """
     Parses string representations of lists in DataFrame columns to actual NumPy arrays.
  
@@ -58,6 +58,19 @@ def process_file(data_input: Union[str, pd.DataFrame] , file_format= str, to_lis
  
                 data[ColName] = pd.to_numeric(data[ColName], errors='coerce')
                 print("System : Done!")
+                print("-" * 50)
+
+
+
+        elif len(data[data[ColName].apply(str).str.isnumeric()]) >= len(data[data[ColName].apply(str).str.isnumeric() == False]):
+
+            print(f"WARNING:\nThis Dataset Name ({data_input.split('\\')[-1]}) Found numbers as {len(data[ColName].apply(type).unique())} in a column called ({ColName})\nPath : {data_input}")
+
+            print(f"System : Trying to fix and converting the column as a Numerical Values...")
+            data[ColName] = pd.to_numeric(data[ColName], errors='coerce')
+            print("System : Done!")
+            print("-" * 50)
+
 
         elif isinstance(First_Value , str) and First_Value.strip().startswith("["):
             if to_list:
@@ -66,8 +79,8 @@ def process_file(data_input: Union[str, pd.DataFrame] , file_format= str, to_lis
                 data[f"{ColName.capitalize()}List"] = data[ColName].apply(lambda x : array(literal_eval(x)) if pd.notna(x) else nan)
             data.drop(ColName,inplace=True,axis=1)
             
-    if file_format.strip().lower() in ['csv','txt','tsv','xls','xlsx','json','parquet','pkl','feather','db','sqlite']:
-        _save_as(data=data,ext=file_format)
+    if file_format != None and file_format.strip().lower() in ['csv','txt','tsv','xls','xlsx','json','parquet','pkl','feather','db','sqlite']:
+        save_as(data=data,ext=file_format)
 
 
     return data
@@ -125,7 +138,7 @@ def process_all_files(directory_path: str, output_dir="All CSV Files is Converte
                     if "List" in df_converted.columns[-1]:
                         print(Sub_Item_Path)
                         makedirs(dirname(output),exist_ok=True)
-                        _save_as(data=df_converted,
+                        save_as(data=df_converted,
                                 current_dir=output.replace(f".{Sub_Item_Path.split(".")[-1].strip().lower()}", f".{file_format}"),
                                 ext=file_format,to_list=to_list)
 

{deepcsv-0.6.3 → deepcsv-0.6.4}/deepcsv/utils.py

@@ -3,6 +3,8 @@ import pandas as pd
 from typing import Optional, Union
 from pathlib import Path
 
+__all__ = ['read_any', 'clean_values', 'auto_fix',"save_as"]
+
 # ──────────────────────────────────────────────
 #               PRIVATE HELPERS
 # ──────────────────────────────────────────────
@@ -82,66 +84,6 @@ def _validate_condition(condition):
  
     return op_func, cond_val
 
-def _save_as(data: pd.DataFrame, current_dir = str(Path.cwd()), ext= str) -> None:
-    """
-    Saves a DataFrame to a file with the specified format.
-
-    Parameters
-    ----------
-    data : pd.DataFrame
-        The DataFrame to save.
-    file_path : str
-        Path without extension. Example: "data/myfile"
-    ext : str
-        File extension. Supported:
-        - .csv      → pd.to_csv()
-        - .xlsx     → pd.to_excel()
-        - .json     → pd.to_json()
-        - .parquet  → pd.to_parquet()
-        - .pkl      → pd.to_pickle()
-        - .feather  → pd.to_feather()
-        - .tsv      → pd.to_csv(sep='\\t')
-        - .html     → pd.to_html()
-        - .xml      → pd.to_xml()
-
-    Returns
-    -------
-    None
-
-    Examples
-    --------
-    >>> _save_as(df, "data/myfile", ".parquet")
-    >>> _save_as(df, "data/myfile", ".csv")
-    """
-    ext = ext.strip().lower()
-    if not ext.startswith("."):
-        ext = f".{ext}"
-
-    full_path = f"{current_dir}{ext}"
-
-    writers = {
-        ".csv":     lambda: data.to_csv(full_path, index=False),
-        ".tsv":     lambda: data.to_csv(full_path, sep='\t', index=False),
-        ".xlsx":    lambda: data.to_excel(full_path, index=False),
-        ".json":    lambda: data.to_json(full_path, orient="records", indent=2),
-        ".parquet": lambda: data.to_parquet(full_path, index=False),
-        ".pkl":     lambda: data.to_pickle(full_path),
-        ".feather": lambda: data.to_feather(full_path),
-        ".html":    lambda: data.to_html(full_path, index=False),
-        ".xml":     lambda: data.to_xml(full_path, index=False),
-    }
-
-    writer = writers.get(ext)
-    if writer is None:
-        raise ValueError(
-            f"Unsupported extension: {ext!r}\n"
-            f"Supported: {list(writers.keys())}"
-        )
-
-    writer()
-    print(f"Saved: {full_path}")
-    print("-"*50)
-
 
 def _val_dtype(x,dtype):
     if dtype == str:
@@ -380,4 +322,65 @@ def auto_fix(data_input: Union[str, pd.DataFrame]):
                 df[ColName] = df[ColName].apply(lambda x: _val_dtype(x,dtype))
             print("Done!")
             print("—"*35)
-    return df
+    return df
+
+
+def save_as(data: pd.DataFrame, current_dir = str(Path.cwd()), ext= str) -> None:
+    """
+    Saves a DataFrame to a file with the specified format.
+
+    Parameters
+    ----------
+    data : pd.DataFrame
+        The DataFrame to save.
+    file_path : str
+        Path without extension. Example: "data/myfile"
+    ext : str
+        File extension. Supported:
+        - .csv      → pd.to_csv()
+        - .xlsx     → pd.to_excel()
+        - .json     → pd.to_json()
+        - .parquet  → pd.to_parquet()
+        - .pkl      → pd.to_pickle()
+        - .feather  → pd.to_feather()
+        - .tsv      → pd.to_csv(sep='\\t')
+        - .html     → pd.to_html()
+        - .xml      → pd.to_xml()
+
+    Returns
+    -------
+    None
+
+    Examples
+    --------
+    >>> _save_as(df, "data/myfile", ".parquet")
+    >>> _save_as(df, "data/myfile", ".csv")
+    """
+    ext = ext.strip().lower()
+    if not ext.startswith("."):
+        ext = f".{ext}"
+
+    full_path = f"{current_dir}{ext}"
+
+    writers = {
+        ".csv":     lambda: data.to_csv(full_path, index=False),
+        ".tsv":     lambda: data.to_csv(full_path, sep='\t', index=False),
+        ".xlsx":    lambda: data.to_excel(full_path, index=False),
+        ".json":    lambda: data.to_json(full_path, orient="records", indent=2),
+        ".parquet": lambda: data.to_parquet(full_path, index=False),
+        ".pkl":     lambda: data.to_pickle(full_path),
+        ".feather": lambda: data.to_feather(full_path),
+        ".html":    lambda: data.to_html(full_path, index=False),
+        ".xml":     lambda: data.to_xml(full_path, index=False),
+    }
+
+    writer = writers.get(ext)
+    if writer is None:
+        raise ValueError(
+            f"Unsupported extension: {ext!r}\n"
+            f"Supported: {list(writers.keys())}"
+        )
+
+    writer()
+    print(f"Saved: {full_path}")
+    print("-"*50)

{deepcsv-0.6.3 → deepcsv-0.6.4/deepcsv.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepcsv
-Version: 0.6.3
+Version: 0.6.4
 Summary: Automatically processes data files in directories, converts array-like strings to NumPy arrays, detects and fixes data type issues, and saves results as optimized Parquet files and MORE!
 Home-page: https://github.com/abdubakr77/deepcsv
 Author: Abdullah Bakr
@@ -35,6 +35,13 @@ Dynamic: requires-python
 Dynamic: summary
 
 # deepcsv
+
+![PyPI Downloads](https://img.shields.io/pypi/dm/deepcsv?color=blue&label=Downloads)
+![PyPI Version](https://img.shields.io/pypi/v/deepcsv?color=green&label=Version)
+![Python](https://img.shields.io/pypi/pyversions/deepcsv?color=yellow&label=Python)
+![License](https://img.shields.io/github/license/abdubakr77/deepcsv?color=orange)
+![GitHub Stars](https://img.shields.io/github/stars/abdubakr77/deepcsv?color=yellow)
+
 > *"You think you saved a list. You open it tomorrow — and it's a string."*
 
 `deepcsv` was built to solve exactly this problem.
@@ -245,18 +252,13 @@ auto_fix(data_input: Union[str, pd.DataFrame])
 
 ### Added
 
-- `process_file` — Added Doc & Examples for new params in function
-- `process_all_files` — Added Doc & Examples for new params in function
-- `process_file` & `process_all_file` — Added New parameter `to_list` to be real python list if you don't need array
-- Added `auto_fix` function for automatic data type correction in DataFrames for mixed Dtypes.
-- Added logg to `auto_fix` to track changes made to columns.
-- Added Documentation for `auto_fix` function to understand more about function.
+- `process_file()` — Converting any columns have Numbers as strings to Numerical Values (Float)
+- `save_as` — Added function to save dataset file
 
 ---
 
-### Changed
+### Fixes
 
-- `process_file()` — Changed `save_file_extension` parameter to `file_format`
-- `process_all_files()` — Changed `file_extension` parameter to `file_format`
+- `process_file()` — Fixed some bugs in `file_format` parameter
 
 ---

{deepcsv-0.6.3 → deepcsv-0.6.4}/setup.py

@@ -8,7 +8,7 @@ changelog = (this_directory / "CHANGELOG.md").read_text(encoding="utf-8")
 
 setup(
     name="deepcsv",
-    version="0.6.3",
+    version="0.6.4",
     author="Abdullah Bakr",
     author_email="abdubakora1232@gmail.com",
     description="Automatically processes data files in directories, converts array-like strings to NumPy arrays, detects and fixes data type issues, and saves results as optimized Parquet files and MORE!",

deepcsv-0.6.3/CHANGELOG.md

@@ -1,21 +0,0 @@
-# Changelog
-
----
-
-### Added
-
-- `process_file` — Added Doc & Examples for new params in function
-- `process_all_files` — Added Doc & Examples for new params in function
-- `process_file` & `process_all_file` — Added New parameter `to_list` to be real python list if you don't need array
-- Added `auto_fix` function for automatic data type correction in DataFrames for mixed Dtypes.
-- Added logg to `auto_fix` to track changes made to columns.
-- Added Documentation for `auto_fix` function to understand more about function.
-
----
-
-### Changed
-
-- `process_file()` — Changed `save_file_extension` parameter to `file_format`
-- `process_all_files()` — Changed `file_extension` parameter to `file_format`
-
----

deepcsv-0.6.3/deepcsv/__init__.py

@@ -1,17 +0,0 @@
-from .deepcsv import process_all_files, process_file
-from .utils import read_any, clean_values
-from importlib.metadata import version
-import requests
-
-def _check_for_updates():
-    try:
-        response = requests.get("https://pypi.org/pypi/deepcsv/json")
-        latest = response.json()["info"]["version"]
-        current = version("deepcsv")
-        if latest != current:
-            print(f"DeepCSV: New version {latest} available! — run 'pip install -U deepcsv'")
-    except Exception:
-        pass
-
-
-_check_for_updates()