Merge branch 'development' into release/v0.1.0

src/pymatlib/core/data_handler.py

@@ -109,24 +109,35 @@ def read_data_from_file(file_config: Union[str, Dict], header: bool = True) -> T
 
     Args:
         file_config: Either a path string or a dictionary containing file configuration
-            If dictionary, required keys:
+            If string (direct path):
+                - File must have exactly 2 columns
+                - First column is temperature, second is property
+            If dictionary:
                 - file: Path to data file
                 - temp_col: Temperature column name/index
                 - prop_col: Property column name/index
-            If string, treated as direct file path
         header (bool): Indicates if the file contains a header row.
 
     Returns:
         Tuple[np.ndarray, np.ndarray]: Temperature and property arrays
+
+    Raises:
+        ValueError: If:
+            - For direct path: Data doesn't have exactly two columns
+            - For dictionary config: Specified column names don't match headers
+            - Data contains NaN values
+            - Data contains duplicate temperature entries
     """
     # Handle string (direct path) or dictionary configuration
     if isinstance(file_config, str):
         file_path = file_config
+        direct_path = True
         # For direct file paths, assume first two columns are temperature and property
         temp_col = 0
         prop_col = 1
     else:
         file_path = file_config['file']
+        direct_path = False
         temp_col = file_config['temp_col']
         prop_col = file_config['prop_col']
 
@@ -138,35 +149,111 @@ def read_data_from_file(file_config: Union[str, Dict], header: bool = True) -> T
         # Use pandas read_csv for CSV files
         df = pd.read_csv(file_path, header=0 if header else None)
     else:
-        # For txt files, assume columns are space/tab separated
-        data = np.loadtxt(file_path, dtype=float, skiprows=1 if header else 0)
-        if data.ndim != 2:
-            raise ValueError("Data should be two-dimensional")
-
-        # Handle both column name (which would be an index for txt files) and column index
-        if isinstance(temp_col, int):
-            temp = data[:, temp_col]
-        else:
-            temp = data[:, 0]  # Default to first column
-
-        if isinstance(prop_col, int):
-            prop = data[:, prop_col]
+        # For txt files
+        if header:
+            # Read the header line to get column names
+            with open(file_path, 'r') as f:
+                header_line = f.readline().strip()
+                column_names = header_line.split()
+
+            # Now read the data
+            data = np.loadtxt(file_path, dtype=float, skiprows=1)
+
+            # Direct path case - check for exactly 2 columns
+            if direct_path:
+                if data.shape[1] != 2:
+                    raise ValueError(f"Data should have exactly two columns, but found {data.shape[1]} columns")
+                temp = data[:, 0]
+                prop = data[:, 1]
+            # Dictionary case - match column names
+            else:
+                # Handle temperature column
+                if isinstance(temp_col, str):
+                    if temp_col in column_names:
+                        temp_idx = column_names.index(temp_col)
+                    else:
+                        raise ValueError(f"Temperature column '{temp_col}' not found in file. "
+                                         f"Available columns: {', '.join(column_names)}")
+                else:
+                    if temp_col >= data.shape[1]:
+                        raise ValueError(f"Temperature column index {temp_col} out of bounds (file has {data.shape[1]} columns)")
+                    temp_idx = temp_col
+
+                # Handle property column
+                if isinstance(prop_col, str):
+                    if prop_col in column_names:
+                        prop_idx = column_names.index(prop_col)
+                    else:
+                        raise ValueError(f"Property column '{prop_col}' not found in file. "
+                                         f"Available columns: {', '.join(column_names)}")
+                else:
+                    if prop_col >= data.shape[1]:
+                        raise ValueError(f"Property column index {prop_col} out of bounds (file has {data.shape[1]} columns)")
+                    prop_idx = prop_col
+
+                temp = data[:, temp_idx]
+                prop = data[:, prop_idx]
         else:
-            prop = data[:, 1]  # Default to second column
+            # No header
+            data = np.loadtxt(file_path, dtype=float, skiprows=0)
+
+            # Direct path case - check for exactly 2 columns
+            if direct_path:
+                if data.shape[1] != 2:
+                    raise ValueError(f"Data should have exactly two columns, but found {data.shape[1]} columns")
+                temp = data[:, 0]
+                prop = data[:, 1]
+            # Dictionary case - use column indices
+            else:
+                if isinstance(temp_col, str):
+                    raise ValueError(f"Column name '{temp_col}' specified, but file has no header row")
+                if isinstance(prop_col, str):
+                    raise ValueError(f"Column name '{prop_col}' specified, but file has no header row")
+
+                if temp_col >= data.shape[1]:
+                    raise ValueError(f"Temperature column index {temp_col} out of bounds (file has {data.shape[1]} columns)")
+                if prop_col >= data.shape[1]:
+                    raise ValueError(f"Property column index {prop_col} out of bounds (file has {data.shape[1]} columns)")
+
+                temp = data[:, temp_col]
+                prop = data[:, prop_col]
+
+        # Check for NaN values
+        if np.any(np.isnan(temp)) or np.any(np.isnan(prop)):
+            nan_rows = np.where(np.isnan(temp) | np.isnan(prop))[0] + 1
+            raise ValueError(f"Data contains NaN values in rows: {', '.join(map(str, nan_rows))}")
+
+        # Check for duplicate temperatures
+        unique_temp, counts = np.unique(temp, return_counts=True)
+        duplicates = unique_temp[counts > 1]
+        if len(duplicates) > 0:
+            duplicate_rows = [str(idx + 1) for idx, value in enumerate(temp) if value in duplicates]
+            raise ValueError(f"Duplicate temperature entries found in rows: {', '.join(duplicate_rows)}")
 
-        # Skip the pandas processing below
         return temp, prop
 
     # Process pandas DataFrame (for both Excel and CSV)
     # Handle both column name (string) and column index (integer)
     if isinstance(temp_col, str):
-        temp = df[temp_col].to_numpy(dtype=np.float64)
+        if temp_col in df.columns:
+            temp = df[temp_col].to_numpy(dtype=np.float64)
+        else:
+            raise ValueError(f"Temperature column '{temp_col}' not found in file. "
+                             f"Available columns: {', '.join(df.columns)}")
     else:
+        if temp_col >= len(df.columns):
+            raise ValueError(f"Temperature column index {temp_col} out of bounds (file has {len(df.columns)} columns)")
         temp = df.iloc[:, temp_col].to_numpy(dtype=np.float64)
 
     if isinstance(prop_col, str):
-        prop = df[prop_col].to_numpy(dtype=np.float64)
+        if prop_col in df.columns:
+            prop = df[prop_col].to_numpy(dtype=np.float64)
+        else:
+            raise ValueError(f"Property column '{prop_col}' not found in file. "
+                             f"Available columns: {', '.join(df.columns)}")
     else:
+        if prop_col >= len(df.columns):
+            raise ValueError(f"Property column index {prop_col} out of bounds (file has {len(df.columns)} columns)")
         prop = df.iloc[:, prop_col].to_numpy(dtype=np.float64)
 
     # Check for NaN values

tests/python/test_data_handler.py

 import pytest
 import numpy as np
 from pymatlib.core.data_handler import (
-    read_data, celsius_to_kelvin, fahrenheit_to_kelvin,
+    read_data_from_txt, celsius_to_kelvin, fahrenheit_to_kelvin,
     thousand_times
 )
 
@@ -35,7 +35,7 @@ def test_read_data(tmp_path):
 3.0 30.0
 """)
 
-    temp, prop = read_data(str(test_file))
+    temp, prop = read_data_from_txt(str(test_file))
     assert np.allclose(temp, [1.0, 2.0, 3.0])
     assert np.allclose(prop, [10.0, 20.0, 30.0])
 
@@ -48,7 +48,7 @@ NaN 20.0
 """)
 
     with pytest.raises(ValueError, match="Data contains NaN values in rows: 2"):
-        read_data(str(invalid_file))
+        read_data_from_txt(str(invalid_file))
 
 def test_read_data_errors(tmp_path):
     """Test error handling in read_data function."""
@@ -77,10 +77,10 @@ NaN 20.0
 
     # Test each error case
     with pytest.raises(ValueError, match="Data should have exactly two columns"):
-        temp, prop = read_data(str(wrong_columns))
+        temp, prop = read_data_from_txt(str(wrong_columns))
 
     with pytest.raises(ValueError, match="Data contains NaN values"):
-        temp, prop = read_data(str(nan_file))
+        temp, prop = read_data_from_txt(str(nan_file))
 
     with pytest.raises(ValueError, match="Duplicate temperature entries found"):
-        temp, prop = read_data(str(duplicate_file))
+        temp, prop = read_data_from_txt(str(duplicate_file))