DiadFit 1.0.11__py3-none-any.whl → 1.0.12__py3-none-any.whl

DiadFit/_version.py

@@ -5,4 +5,4 @@
 # 1) we don't load dependencies by storing it in __init__.py
 # 2) we can import it in setup.py for the same reason
 # 3) we can import it into your module
-__version__ = '1.0.11'
+__version__ = '1.0.12'

DiadFit/argon_lines.py

@@ -623,5 +623,324 @@ def calculate_Ar_line_positions(wavelength=532.05, cut_off_intensity=2000):
     return df_Ar_r
 
 
+## Function that is basically just the Ne function but with some renaming.
+
+
+def loop_Ar_lines(*, files, spectra_path, filetype, config_ID_peaks, config, df_fit_params,  prefix, plot_figure=True, print_df=False, const_params=True):
+    # Call the Neon line processing function
+    df_ne = loop_Ne_lines(
+        files=files,
+        spectra_path=spectra_path,
+        filetype=filetype,
+        config_ID_peaks=config_ID_peaks,
+        config=config,
+        df_fit_params=df_fit_params,
+        prefix=prefix,
+        plot_figure=plot_figure,
+        print_df=False,
+        const_params=const_params
+    )
+
+
+
+    # Rename columns by replacing 'Ne' with 'Ar'
+    df_ar = df_ne.rename(columns=lambda col: col.replace('Ne', 'Ar'))
+
+    return df_ar
+
+
+def Argon_id_config(*, height, distance, prominence, width, threshold,
+                    peak1_cent, peak2_cent, n_peaks,
+                    exclude_range_1=None, exclude_range_2=None):
+    return Neon_id_config(
+        height=height,
+        distance=distance,
+        prominence=prominence,
+        width=width,
+        threshold=threshold,
+        peak1_cent=peak1_cent,
+        peak2_cent=peak2_cent,
+        n_peaks=n_peaks,
+        exclude_range_1=exclude_range_1,
+        exclude_range_2=exclude_range_2
+    )
+
+def identify_Ar_lines(*, path, filename, filetype, config, print_df=False):
+    return identify_Ne_lines(
+        path=path,
+        filename=filename,
+        filetype=filetype,
+        config=config,
+        print_df=print_df
+    )
+
+def Ar_peak_config(**kwargs):
+    return Ne_peak_config(**kwargs)
+
+
+def fit_Ar_lines(*, Ar, filename, path, prefix=False, config,
+                 Ar_center_1, Ar_center_2,
+                 Ar_prom_1, Ar_prom_2,
+                 const_params=False):
+    # Call the Neon version internally
+    df_ne = fit_Ne_lines(
+        Ne=Ar,
+        filename=filename,
+        path=path,
+        prefix=prefix,
+        config=config,
+        Ne_center_1=Ar_center_1,
+        Ne_center_2=Ar_center_2,
+        Ne_prom_1=Ar_prom_1,
+        Ne_prom_2=Ar_prom_2,
+        const_params=const_params
+    )
+
+    # Rename output columns from 'Ne' to 'Ar'
+    df_ar = df_ne.rename(columns=lambda col: col.replace('Ne', 'Ar'))
+
+    return df_ar
+
+
+import matplotlib.pyplot as plt
+
+def plot_Ar_corrections(df=None, x_axis=None, x_label='index', marker='o', mec='k', mfc='r'):
+    """
+    Plot correction-related information for Ar spectra.
+    Assumes column names have 'Ar_Corr', '1σ_Ar_Corr', etc.
+    """
+    if x_axis is not None:
+        x = x_axis
+    else:
+        x = df.index
+
+    fig, ((ax5, ax6),  (ax3, ax4), (ax1, ax2)) = plt.subplots(3, 2, figsize=(10, 12))
+
+    # Peak 1
+    ax5.errorbar(x, df['pk1_peak_cent'], xerr=0, yerr=df['error_pk1'].fillna(0).infer_objects(),
+                 fmt='o', ecolor='k', elinewidth=0.8, mfc='b', ms=5, mec='k', capsize=3)
+    ax5.set_xlabel(x_label)
+    ax5.set_ylabel('Peak 1 center')
+
+    # Peak 2
+    ax6.plot(x, df['pk2_peak_cent'], marker, mec=mec, mfc=mfc)
+    ax6.errorbar(x, df['pk2_peak_cent'], xerr=0, yerr=df['error_pk2'].fillna(0).infer_objects(),
+                 fmt='o', ecolor='k', elinewidth=0.8, mfc=mfc, ms=5, mec=mec, capsize=3)
+    ax6.set_xlabel(x_label)
+    ax6.set_ylabel('Peak 2 center')
+
+    # Correction vs. Peak 2
+    ax3.errorbar(df['Ar_Corr'], df['pk2_peak_cent'],
+                 xerr=df['1σ_Ar_Corr'].fillna(0).infer_objects(),
+                 yerr=df['error_pk2'].fillna(0).infer_objects(),
+                 fmt='o', ecolor='k', elinewidth=0.8, mfc='b', ms=5, mec='k', capsize=3)
+    ax3.set_xlabel('Ar Correction factor')
+    ax3.set_ylabel('Peak 2 center')
+
+    # Correction vs. Peak 1
+    ax4.errorbar(df['Ar_Corr'], df['pk1_peak_cent'],
+                 xerr=df['1σ_Ar_Corr'].fillna(0).infer_objects(),
+                 yerr=df['error_pk1'].fillna(0).infer_objects(),
+                 fmt='o', ecolor='k', elinewidth=0.8, mfc='b', ms=5, mec='k', capsize=3)
+    ax4.set_xlabel('Ar Correction factor')
+    ax4.set_ylabel('Peak 1 center')
+
+    # Ar Correction vs. x
+    ax1.errorbar(x, df['Ar_Corr'], xerr=0, yerr=df['1σ_Ar_Corr'].fillna(0).infer_objects(),
+                 fmt='o', ecolor='k', elinewidth=0.8, mfc='grey', ms=5, mec='k', capsize=3)
+    ax1.set_ylabel('Ar Correction factor')
+    ax1.set_xlabel(x_label)
+
+    # Ar Correction vs. residuals (placeholder logic — update as needed)
+    if 'residual_sum' in df.columns:
+        ax2.errorbar(df['residual_sum'], df['Ar_Corr'],
+                     xerr=0, yerr=df['1σ_Ar_Corr'].fillna(0).infer_objects(),
+                     fmt='o', ecolor='k', elinewidth=0.8, mfc='grey', ms=5, mec='k', capsize=3)
+
+    ax2.set_xlabel('Sum of pk1 and pk2 residual')
+    ax2.set_ylabel('Ar Correction factor')
+
+    for ax in [ax1, ax2, ax3, ax4, ax5, ax6]:
+        ax.ticklabel_format(useOffset=False)
+
+    plt.setp(ax3.get_xticklabels(), rotation=30, ha='right')
+    plt.setp(ax4.get_xticklabels(), rotation=30, ha='right')
+
+    fig.tight_layout()
+    return fig
+
+
+def filter_Ar_Line_neighbours(*, df_combo=None, Corr_factor=None, number_av=6, offset=0.00005, file_name_filt=None):
+    """
+    Filters Ar correction factors that deviate by more than `offset` from the
+    local median of neighboring values (defined by `number_av`).
+    Optionally excludes specified filenames via `file_name_filt`.
+    """
+    if df_combo is not None:
+        Corr_factor = df_combo['Ar_Corr']
+
+    Corr_factor_Filt = np.zeros(len(Corr_factor), dtype=float)
+    median_loop = np.zeros(len(Corr_factor), dtype=float)
+
+    for i in range(len(Corr_factor)):
+        if i < len(Corr_factor) / 2:
+            median_loop[i] = np.nanmedian(Corr_factor[i:i+number_av])
+        else:
+            median_loop[i] = np.nanmedian(Corr_factor[i-number_av:i])
+
+        if (
+            Corr_factor[i] > (median_loop[i] + offset)
+            or Corr_factor[i] < (median_loop[i] - offset)
+        ):
+            Corr_factor_Filt[i] = np.nan
+        else:
+            Corr_factor_Filt[i] = Corr_factor[i]
+
+    ds = pd.Series(Corr_factor_Filt)
+
+    if file_name_filt is not None:
+        pattern = '|'.join(file_name_filt)
+        mask = df_combo['filename_x'].str.contains(pattern)
+        ds = ds.where(~mask, np.nan)
+
+    return ds
+
+
+def generate_Ar_corr_model(*, time, Ar_corr, N_poly=3, CI=0.67, bootstrap=False,
+                           std_error=True, N_bootstrap=500,
+                           save_fig=False, pkl_name='polyfit_data_Ar.pkl'):
+    """Generates a polynomial correction model for Ar correction data."""
+
+    x_all = np.array([time])
+
+    if isinstance(Ar_corr, pd.DataFrame):
+        y_all = np.array([Ar_corr['Ar_Corr']])
+        y_err = Ar_corr['1σ_Ar_Corr']
+    else:
+        y_all = Ar_corr
+        y_err = 0 * Ar_corr
+
+    non_nan_indices = ~np.isnan(x_all) & ~np.isnan(y_all)
+    x = x_all[non_nan_indices]
+    y = y_all[non_nan_indices]
+
+    coefficients = np.polyfit(x, y, N_poly)
+    Pf = np.poly1d(coefficients)
+
+    data = {'model': Pf, 'x': x, 'y': y}
+    with open(pkl_name, 'wb') as f:
+        pickle.dump(data, f)
+
+    new_x_plot = np.linspace(np.min(x), np.max(x), 100)
+
+    if bootstrap:
+        Ar_corr2 = calculate_Ar_corr_bootstrap_values(
+            pickle_str=pkl_name,
+            new_x=pd.Series(new_x_plot),
+            N_poly=N_poly,
+            CI=CI,
+            N_bootstrap=N_bootstrap
+        )
+    elif std_error:
+        Ar_corr2 = calculate_Ar_corr_std_err_values(
+            pickle_str=pkl_name,
+            new_x=pd.Series(new_x_plot),
+            CI=CI
+        )
+
+    fig, ax1 = plt.subplots(1, 1, figsize=(10, 5))
+    ax1.errorbar(x, y, xerr=0, yerr=y_err, fmt='o', ecolor='k',
+                 elinewidth=0.8, mfc='grey', ms=5, mec='k', capsize=3)
+
+    ax1.plot(new_x_plot, Ar_corr2['preferred_values'], '-k', label='best fit')
+    ax1.plot(new_x_plot, Ar_corr2['lower_values'], ':k', label='lower bound')
+    ax1.plot(new_x_plot, Ar_corr2['upper_values'], ':k', label='upper bound')
+    ax1.plot(x, y, '+r', label='Ar lines')
+
+    ax1.set_xlabel('sec after midnight')
+    ax1.set_ylabel('Ar Corr factor')
+    ax1.ticklabel_format(useOffset=False)
+    ax1.legend()
+
+    suffix = {1: 'st', 2: 'nd', 3: 'rd'}.get(N_poly, 'th')
+    ax1.set_title(f"{N_poly}$^{{{suffix}}}$ degree polynomial: {int(CI * 100)}% prediction interval")
+
+    if save_fig:
+        fig.savefig('Ar_line_correction.png')
+
+    return Pf, fig
+
+
+def calculate_Ar_corr_std_err_values(*, pickle_str, new_x, CI=0.67):
+    with open(pickle_str, 'rb') as f:
+        data = pickle.load(f)
+
+    model = data['model']
+    N_poly = model.order - 1
+    x = data['x']
+    y = data['y']
+
+    new_x_array = np.asarray(new_x)
+    residuals = y - model(x)
+    residual_std = np.std(residuals)
+
+    mean_x = np.mean(x)
+    n = len(x)
+    standard_errors = residual_std * np.sqrt(1 + 1/n + (new_x_array - mean_x)**2 / np.sum((x - mean_x)**2))
+
+    df_dof = len(x) - (N_poly + 1)
+    t_value = t.ppf((1 + CI) / 2, df_dof)
+
+    preferred_values = model(new_x_array)
+    lower_values = preferred_values - t_value * standard_errors
+    upper_values = preferred_values + t_value * standard_errors
+
+    return pd.DataFrame({
+        'time': new_x_array,
+        'preferred_values': preferred_values,
+        'lower_values': lower_values,
+        'upper_values': upper_values
+    })
+
+
+def calculate_Ar_corr_bootstrap_values(*, pickle_str, new_x, N_poly=3, CI=0.67, N_bootstrap=500):
+    with open(pickle_str, 'rb') as f:
+        data = pickle.load(f)
+
+    Pf = data['model']
+    x = data['x']
+    y = data['y']
+
+    x_values = new_x
+    preferred_values = []
+    lower_values = []
+    upper_values = []
+
+    for new_x in x_values:
+        bootstrap_predictions = []
+        for _ in range(N_bootstrap):
+            bootstrap_indices = np.random.choice(len(x), size=len(x), replace=True)
+            bootstrap_x = x[bootstrap_indices]
+            bootstrap_y = y[bootstrap_indices]
+            bootstrap_coefficients = np.polyfit(bootstrap_x, bootstrap_y, N_poly)
+            bootstrap_Pf = np.poly1d(bootstrap_coefficients)
+            bootstrap_predictions.append(bootstrap_Pf(new_x))
+
+        bootstrap_predictions_sorted = np.sort(bootstrap_predictions)
+        lower_idx = int(((1 - CI) / 2) * N_bootstrap)
+        upper_idx = int((1 - (1 - CI) / 2) * N_bootstrap)
+
+        preferred_values.append(Pf(new_x))
+        lower_values.append(bootstrap_predictions_sorted[lower_idx])
+        upper_values.append(bootstrap_predictions_sorted[upper_idx])
+
+    return pd.DataFrame({
+        'time': x_values,
+        'preferred_values': preferred_values,
+        'lower_values': lower_values,
+        'upper_values': upper_values
+    })
+
+
 
 

DiadFit/densimeters.py

@@ -976,7 +976,7 @@ def merge_fit_files(path):
 ## New UC Berkeley using 1220
 
 def calculate_density_ucb(*, Ne_line_combo='1117_1447', df_combo=None, temp='SupCrit', 
-CI_split=0.67, CI_neon=0.67,  Ne_pickle_str=None, pref_Ne=None, Ne_err=None, corrected_split=None, split_err=None):
+CI_split=0.67, CI_neon=0.67,  Ne_pickle_str=None, Ar_pickle_str=None, pref_Ne=None, Ne_err=None, corrected_split=None, split_err=None):
     """ This function converts Diad Splitting into CO$_2$ density using the UC Berkeley calibration line
     developed by DeVitre and Wieser in 2023. 
 
@@ -1339,28 +1339,41 @@ CI_split=0.67, CI_neon=0.67,  Ne_pickle_str=None, pref_Ne=None, Ne_err=None, cor
     df_merge = df_merge.rename(columns={'filename_x': 'filename'})
 
 
-    #
-    #
-
-    if Ne_pickle_str is not None: # If its not none, have all the columns for Ne
-        cols_to_move = ['filename', 'Density g/cm3', 'σ Density g/cm3','σ Density g/cm3 (from Ne+peakfit)', 'σ Density g/cm3 (from densimeter)',
-        'Corrected_Splitting', 'Corrected_Splitting_σ',
-        'Corrected_Splitting_σ_Ne', 'Corrected_Splitting_σ_peak_fit', 'power (mW)', 'Spectral Center']
-        df_merge = df_merge[cols_to_move + [
-            col for col in df_merge.columns if col not in cols_to_move]]
-    elif pref_Ne is not None and df_combo is not None: #If Pref Ne, 
-        cols_to_move = ['filename', 'Density g/cm3', 'σ Density g/cm3','σ Density g/cm3 (from Ne+peakfit)', 'σ Density g/cm3 (from densimeter)',
-        'Corrected_Splitting', 'Corrected_Splitting_σ',
-        'Corrected_Splitting_σ_Ne', 'Corrected_Splitting_σ_peak_fit']
-        df_merge = df_merge[cols_to_move + [
-            col for col in df_merge.columns if col not in cols_to_move]]
-            
+    # NE or Ar. 
+    
+    if Ne_pickle_str is not None:
+        cols_to_move = [
+            'filename', 'Density g/cm3', 'σ Density g/cm3',
+            'σ Density g/cm3 (from Ne+peakfit)', 'σ Density g/cm3 (from densimeter)',
+            'Corrected_Splitting', 'Corrected_Splitting_σ',
+            'Corrected_Splitting_σ_Ne', 'Corrected_Splitting_σ_peak_fit',
+            'power (mW)', 'Spectral Center'
+        ]
+    elif Ar_pickle_str is not None:
+        cols_to_move = [
+            'filename', 'Density g/cm3', 'σ Density g/cm3',
+            'σ Density g/cm3 (from Ar+peakfit)', 'σ Density g/cm3 (from densimeter)',
+            'Corrected_Splitting', 'Corrected_Splitting_σ',
+            'Corrected_Splitting_σ_Ar', 'Corrected_Splitting_σ_peak_fit',
+            'power (mW)', 'Spectral Center'
+        ]
+    elif pref_Ne is not None and df_combo is not None:
+        cols_to_move = [
+            'filename', 'Density g/cm3', 'σ Density g/cm3',
+            'σ Density g/cm3 (from Ne+peakfit)', 'σ Density g/cm3 (from densimeter)',
+            'Corrected_Splitting', 'Corrected_Splitting_σ',
+            'Corrected_Splitting_σ_Ne', 'Corrected_Splitting_σ_peak_fit'
+        ]
     elif df_combo is None:
         
         cols_to_move = ['Density g/cm3', 'σ Density g/cm3','σ Density g/cm3 (from Ne+peakfit)', 'σ Density g/cm3 (from densimeter)',
         'Corrected_Splitting']
-        df_merge = df_merge[cols_to_move + [
-            col for col in df_merge.columns if col not in cols_to_move]]
+
+    
+    # Move only existing columns to the front
+    cols_existing = [col for col in cols_to_move if col in df_merge.columns]
+    df_merge = df_merge[cols_existing + [col for col in df_merge.columns if col not in cols_existing]]
+
 
 
 
@@ -2050,4 +2063,123 @@ def apply_and_save_vertical_shift_to_ucb_densimeter(new_x, new_y):
 
 
     return shift
+    
+    
+## Corrected splitting calculator for Argon
+def propagate_error_split_argon_peakfit(*, df_fits, Ar_corr=None, Ar_err=None, pref_Ar=None):
+    """ This function propagates errors in your Ar correction model and peak fits by quadrature.
+
+    Parameters
+    -----------------
+
+    df_fits: pd.DataFrame
+        Dataframe of peak fitting parameters. Must contain columns for 'Diad1_cent_err', 'Diad2_cent_err', 'Splitting'
+
+    Choose either:
+
+    Ar_corr: pd.DataFrame (Optional)
+        Dataframe with columns for 'upper_values' and 'lower values', e.g. the upper and lower bounds of the error on the Ar correction model
+
+    Or
+
+    pref_Ar and Ar_err: float, int, pd.Series, np.array
+        A preferred value of the Ar correction factor and the error (e.g. pref_Ar=0.998, Ar_err=0.001). Used for
+        rapid peak fitting before developing Ar lines.
+
+    Returns
+    -----------------
+    two pd.Series: the error on the splitting, and the combined error from the splitting and the Ar correction model.
+
+    """
+    # Get the error on Argon things
+    if isinstance(Ar_corr, pd.DataFrame):
+        Ar_err = (Ar_corr['upper_values'] - Ar_corr['lower_values']) / 2
+        print(np.mean(Ar_err))
+        pref_Ar = Ar_corr['preferred_values']
+
+    elif pref_Ar is not None and Ar_err is not None:
+        print('using fixed values for Ar error and Ar factor')
+    else:
+        raise TypeError('You must either provide Ar_corr as a dataframe, or provide pref_Ar and Ar_err as values.')
+
+    # Get the peak fit errors
+    Diad1_err = df_fits['Diad1_cent_err'].fillna(0).infer_objects()
+    Diad2_err = df_fits['Diad2_cent_err'].fillna(0).infer_objects()
+    split_err = (Diad1_err**2 + Diad2_err**2)**0.5
+
+    # Propagate uncertainty from Ar correction and peak fits
+    Combo_err = (((df_fits['Splitting'] * Ar_err)**2) + (pref_Ar * split_err)**2)**0.5
+
+    return Combo_err, split_err
+    
+def calculate_Ar_corr_std_err_values(*, pickle_str, new_x, CI=0.67):
+    # Load the model and the data from the pickle file
+    with open(pickle_str, 'rb') as f:
+        data = pickle.load(f)
+
+    model = data['model']
+    N_poly = model.order - 1
+
+    Pf = data['model']
+    x = data['x']
+    y = data['y']
+
+    # Convert new_x to plain numpy array
+    new_x_array = np.asarray(new_x)
+
+    # Calculate the residuals
+    residuals = y - Pf(x)
+
+    # Calculate the standard deviation of the residuals
+    residual_std = np.std(residuals)
+
+    # Calculate the standard errors for the new x values
+    mean_x = np.mean(x)
+    n = len(x)
+    standard_errors = residual_std * np.sqrt(1 + 1/n + (new_x_array - mean_x)**2 / np.sum((x - mean_x)**2))
+
+    # Calculate the degrees of freedom
+    df_dof = len(x) - (N_poly + 1)
+
+    # Calculate the t value for the given confidence level
+    t_value = t.ppf((1 + CI) / 2, df_dof)
+
+    # Calculate the prediction intervals
+    preferred_values = Pf(new_x_array)
+    lower_values = preferred_values - t_value * standard_errors
+    upper_values = preferred_values + t_value * standard_errors
+
+    df_out = pd.DataFrame(data={
+        'time': new_x_array,
+        'preferred_values': preferred_values,
+        'lower_values': lower_values,
+        'upper_values': upper_values
+    })
+
+    return df_out
+
+    
+def calculate_corrected_splitting_argon(*, df_combo_c, Ar_pickle_str, CI):
+    
+    time=df_combo_c['sec since midnight']
+    Ar_corr = calculate_Ar_corr_std_err_values(pickle_str=Ar_pickle_str, new_x=time, CI=CI)
+    
+    Split=df_combo_c['Splitting']*Ar_corr['preferred_values']
+    df_combo_c['Corrected_Splitting']=Split
+    
+    
+    # Extract preferred correction values
+    pref_Ar = Ar_corr['preferred_values']
+    Split_err, pk_err = propagate_error_split_argon_peakfit(Ar_corr=Ar_corr, df_fits=df_combo_c)
+    
+    # Add Ar-specific columns to the DataFrame
+    df_combo_c['Corrected_Splitting_σ'] = Split_err
+    df_combo_c['Corrected_Splitting_σ_Ar'] = (
+        (Ar_corr['upper_values'] * df_combo_c['Splitting'] -
+        Ar_corr['lower_values'] * df_combo_c['Splitting']) / 2
+    )
+    df_combo_c['Corrected_Splitting_σ_peak_fit'] = pk_err
+    
+    return df_combo_c
+        
 

DiadFit/importing_data_files.py

@@ -496,85 +496,176 @@ creation=creation, modification=modification)
 ## Functions to extract things for HORIBA
 
 ## HORIBA acquisition time
-encode="ISO-8859-1"
-def extract_duration_horiba(*, path, filename):
-    """ This function extracts the duration from a HORIBA file by finding the line starting with #Acq. """
-    fr = open(path+'/'+filename,  'r', encoding=encode)
+# encode="ISO-8859-1"
+# def extract_duration_horiba(*, path, filename):
+#     """ This function extracts the duration from a HORIBA file by finding the line starting with #Acq. """
+#     fr = open(path+'/'+filename,  'r', encoding=encode)
+# 
+#     while True:
+#         l=fr.readline()
+#         if l.startswith('#Acq.'):
+#             line=l
+#             break
+#     return line
+# 
+# def extract_accumulations_horiba(*, path, filename):
+#     """ This function extracts the accumulations from a HORIBA file by finding the line starting with #Accumu. """
+#     fr = open(path+'/'+filename,  'r', encoding=encode)
+# 
+#     while True:
+#         l=fr.readline()
+#         if l.startswith('#Accumu'):
+#             line=l
+#             break
+#     return line
+# 
+# def extract_objective_horiba(*, path, filename):
+#     """ This function extracts the objective used from a HORIBA file by finding the line starting with #Object. """
+#     fr = open(path+'/'+filename,  'r', encoding=encode)
+# 
+#     while True:
+#         l=fr.readline()
+#         if l.startswith('#Object'):
+#             line=l
+#             break
+#     return line
+# 
+# def extract_date_horiba(*, path, filename):
+#     """ This function extracts the date used from a HORIBA file by finding the line starting with #Date. """
+#     fr = open(path+'/'+filename,  'r', encoding=encode)
+# 
+#     while True:
+#         l=fr.readline()
+#         if l.startswith('#Date'):
+#             line=l
+#             break
+#     return line
+# 
+# def extract_spectral_center_horiba(*, path, filename):
+#     """ This function extracts the spectral center used from a HORIBA file by finding the line starting with #Spectro (cm-¹). """
+#     fr = open(path+'/'+filename,  'r', encoding=encode)
+# 
+#     while True:
+#         l=fr.readline()
+#         if l.startswith('#Spectro (cm-¹)'):
+#             line=l
+#             break
+#     return line
+# 
+# def extract_24hr_time_horiba(*, path, filename):
+#     """ This function extracts the 24 hr time from a HORIBA file by finding the line starting with #Acquired. """
+#     fr = open(path+'/'+filename,  'r', encoding=encode)
+# 
+#     while True:
+#         l=fr.readline()
+#         if l.startswith('#Acquired'):
+#             line=l
+#             break
+#     return line
+# 
+# def extract_spectraname_horiba(*, path, filename):
+#     """
+#     This function extracts the spectral name from HORIBA files
+#     """
+#     fr = open(path+'/'+filename,  'r', encoding=encode)
+# 
+#     while True:
+#         l=fr.readline()
+#         if l.startswith('#Title'):
+#             line=l
+#             break
+#     return line
+# 
+# 
 
-    while True:
-        l=fr.readline()
-        if l.startswith('#Acq.'):
-            line=l
-            break
-    return line
+# 
+# 
+# 
+# 
+import numpy as np
 
-def extract_accumulations_horiba(*, path, filename):
-    """ This function extracts the accumulations from a HORIBA file by finding the line starting with #Accumu. """
-    fr = open(path+'/'+filename,  'r', encoding=encode)
+encode = "ISO-8859-1"
 
-    while True:
-        l=fr.readline()
-        if l.startswith('#Accumu'):
-            line=l
-            break
-    return line
+def extract_duration_horiba(*, path, filename):
+    with open(path + '/' + filename, 'r', encoding=encode) as fr:
+        for l in fr:
+            if l.startswith('#Acq.'):
+                return l
+    return np.nan
 
-def extract_objective_horiba(*, path, filename):
-    """ This function extracts the objective used from a HORIBA file by finding the line starting with #Object. """
-    fr = open(path+'/'+filename,  'r', encoding=encode)
+def extract_accumulations_horiba(*, path, filename):
+    with open(path + '/' + filename, 'r', encoding=encode) as fr:
+        for l in fr:
+            if l.startswith('#Accumulations'):
+                return l
+    return np.nan
 
-    while True:
-        l=fr.readline()
-        if l.startswith('#Object'):
-            line=l
-            break
-    return line
+def extract_objective_horiba(*, path, filename):
+    with open(path + '/' + filename, 'r', encoding=encode) as fr:
+        for l in fr:
+            if l.startswith('#Objective'):
+                return l
+    return np.nan
 
 def extract_date_horiba(*, path, filename):
-    """ This function extracts the date used from a HORIBA file by finding the line starting with #Date. """
-    fr = open(path+'/'+filename,  'r', encoding=encode)
-
-    while True:
-        l=fr.readline()
-        if l.startswith('#Date'):
-            line=l
-            break
-    return line
+    with open(path + '/' + filename, 'r', encoding=encode) as fr:
+        for l in fr:
+            if l.startswith('#Date'):
+                return l
+    return np.nan
 
 def extract_spectral_center_horiba(*, path, filename):
-    """ This function extracts the spectral center used from a HORIBA file by finding the line starting with #Spectro (cm-¹). """
-    fr = open(path+'/'+filename,  'r', encoding=encode)
+    with open(path + '/' + filename, 'r', encoding=encode) as fr:
+        for l in fr:
+            if l.startswith('#Spectro (cm-¹)'):
+                try:
+                    return float(l.split('=')[1].strip())
+                except (IndexError, ValueError):
+                    return np.nan
+    return np.nan
 
-    while True:
-        l=fr.readline()
-        if l.startswith('#Spectro (cm-¹)'):
-            line=l
-            break
-    return line
 
 def extract_24hr_time_horiba(*, path, filename):
-    """ This function extracts the 24 hr time from a HORIBA file by finding the line starting with #Acquired. """
-    fr = open(path+'/'+filename,  'r', encoding=encode)
-
-    while True:
-        l=fr.readline()
-        if l.startswith('#Acquired'):
-            line=l
-            break
-    return line
+    with open(path + '/' + filename, 'r', encoding=encode) as fr:
+        for l in fr:
+            if l.startswith('#Acquired'):
+                return l
+    return np.nan
 
 def extract_spectraname_horiba(*, path, filename):
+    with open(path + '/' + filename, 'r', encoding=encode) as fr:
+        for l in fr:
+            if l.startswith('#Title'):
+                return l
+    return np.nan
+
+    
+def stitch_metadata_in_loop_horiba(Allfiles, path=None):
+
+    """ Stitches acquisition parameters together from the function extract_acq_params_horiba for multiple files
+    Parameters
+    -------------
+    AllFiles: list
+        List of all file names
+
+    path: str
+        Path where files are found
+
+    Returns
+    -------------
+    df of aquisitoin parameters
     """
-    This function extracts the spectral name from HORIBA files
-    """
-    fr = open(path+'/'+filename,  'r', encoding=encode)
+    if path is None:
+        path=os.getcwd()
+
+    df=pd.DataFrame([])
+    for i in tqdm(range(0, len(Allfiles))):
+        file=Allfiles[i]
+        one_file=extract_acq_params_horiba(path=path, filename=file)
+        df=pd.concat([df, one_file], axis=0)
+    df_out=df.reset_index(drop=True)
+    return df_out
 
-    while True:
-        l=fr.readline()
-        if l.startswith('#Title'):
-            line=l
-            break
-    return line
 
 
 def extract_acq_params_horiba(path, filename):
@@ -604,14 +695,10 @@ def extract_acq_params_horiba(path, filename):
     year=int(date.split('.')[2])
     month_name=calendar.month_name[month]
     Day=datetime.strptime(date, "%d.%m.%Y")
-    spec_cen=extract_spectral_center_horiba(path=path, filename=filename)
-    spec=float(spec_cen.split('=')[1])
 
-    spec_str=extract_spectral_center_horiba(path=path,
+    spec=extract_spectral_center_horiba(path=path,
     filename=filename)
 
-    spec=spec_str.split('\t')[1].split('\n')[0]
-
 
     time_str=extract_24hr_time_horiba(path=path, filename=filename)
     time=time_str.split(' ')[1].split('\n')[0]
@@ -641,36 +728,8 @@ def extract_acq_params_horiba(path, filename):
 
 
     return df
-
-
-
-
-def stitch_metadata_in_loop_horiba(AllFiles, path=None):
-
-    """ Stitches acquisition parameters together from the function extract_acq_params_horiba for multiple files
-    Parameters
-    -------------
-    AllFiles: list
-        List of all file names
-
-    path: str
-        Path where files are found
-
-    Returns
-    -------------
-    df of aquisitoin parameters
-    """
-    if path is None:
-        path=os.getcwd()
-
-    df=pd.DataFrame([])
-    for i in tqdm(range(0, len(AllFiles))):
-        file=AllFiles[i]
-        one_file=extract_acq_params_horiba(path=path, filename=file)
-        df=pd.concat([df, one_file], axis=0)
-    df_out=df.reset_index(drop=True)
-    return df_out
-
+    
+    
 
 
 ## Functions to extract metadata from WITEC files (v instrument specific)

{DiadFit-1.0.11.dist-info → DiadFit-1.0.12.dist-info}/LICENSE.txt

@@ -6,6 +6,10 @@ Permission is hereby granted, free of charge, to any person obtaining a copy of
 
 The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
 
+Citing in Main Text
+
+If you use DiadFit in your study, you must cite it in the main text of your paper. This code took me years to write and presumably is saving you a lot of time. Thus, it deserves to actually recieve a citation, vs just describing its use in the supplement. If I do not get credit for my open source work that means something for promotion/tenure, I will not be able to continue working and building these packages. If you only cite it in the supplement, you must pay for your use of DiadFit, at the rate of $500/study. This will support my spare time to maintain these packages. 
+
 Special Clause on GUI Usage
 
 Use of DiadFit in graphical user interfaces (GUIs), including but not limited to applications that provide point-and-click access to DiadFit’s functions, requires prior written permission from the author.

{DiadFit-1.0.11.dist-info → DiadFit-1.0.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: DiadFit
-Version: 1.0.11
+Version: 1.0.12
 Summary: DiadFit
 Home-page: https://github.com/PennyWieser/DiadFit
 Author: Penny Wieser

{DiadFit-1.0.11.dist-info → DiadFit-1.0.12.dist-info}/RECORD

@@ -29,15 +29,15 @@ DiadFit/Mediumrho_polyfit_data_CCMR.pkl,sha256=U6ODSdurqS0-lynm1MG1zktg8NuhYRbrY
 DiadFit/Mediumrho_polyfit_data_CMASS.pkl,sha256=SBy1pIdqCAF9UtB9FLNTuD0-tFyD7swwJppdE2U_FsY,1557
 DiadFit/Psensor.py,sha256=C2xSlgxhUJIKIBDvUp02QaYRs5QsIqjGGRMP25ZLRZ0,10435
 DiadFit/__init__.py,sha256=F-HjhCYKL_U8PfiH8tZ9DUCkxPvo6lAslJS4fyvxkbY,1148
-DiadFit/_version.py,sha256=yz8r6H20z1GetC4Zn4tV21xqy4lJucguWWWyVy-HmNA,296
-DiadFit/argon_lines.py,sha256=vtzsuDdEgrAmEF9xwpejpFqKV9hKPS1JUYhIl4AfXZ0,7675
+DiadFit/_version.py,sha256=H5d8goZbkob4s3WN42m3x_S_cdOTG_7oVqE8MEDVSs4,296
+DiadFit/argon_lines.py,sha256=yMPmNS2b93t6PeULX72QBnNmam-TZUJRQP0lozYl4pw,18305
 DiadFit/cosmicray_filter.py,sha256=a45x2_nmpi9Qcjc_L39UA9JOd1NMorIjtTRGnCdG3MU,23634
 DiadFit/densimeter_fitting.py,sha256=AV5jWHSuIuN-e61chwMiTETa26pQo5drEGorYTkceHo,8308
-DiadFit/densimeters.py,sha256=1eT6XVYtRPbY4WmEgIvbvEYdDkJTvFlIjoqhypdpDKk,76511
+DiadFit/densimeters.py,sha256=L7q9SmRm1exkCPsSTsbGwACo2afRsReJKyOeaR-FiAw,80982
 DiadFit/density_depth_crustal_profiles.py,sha256=Vvtw3-_xuWIYEuhuDzXstkprluXyBkUcdm9iP7qBwyQ,19754
 DiadFit/diads.py,sha256=gwHWTquJeoJaBYEYjJcJct38j6Bi-GUUsFCPsFgCFzU,179483
 DiadFit/error_propagation.py,sha256=Evka2vsHQmgekO1xft-AkjxvkMdwAVawNVbWSe7SZIQ,50734
-DiadFit/importing_data_files.py,sha256=j7cSEPZ6iKmYnSqYEIcCl7YNdqqkCD56W-4V9T2oWOE,52010
+DiadFit/importing_data_files.py,sha256=r8Lezr0eXcO6P0nmWlb7K_H5yw9Se54rz-tUaNqJpPY,53775
 DiadFit/lookup_table.csv,sha256=Hs1tmSQ9ArTUDv3ymEXbvnLlPBxYUP0P51dz7xAKk-Q,2946857
 DiadFit/lookup_table_noneg.csv,sha256=HelvewKbBy4cqT2GAqsMo-1ps1lBYqZ-8hCJZWPGfhI,3330249
 DiadFit/molar_gas_proportions.py,sha256=3zc5t037L11w_hCYJqV4Xp4NwVCmGb3gMp1McAhV0TM,9315
@@ -45,8 +45,8 @@ DiadFit/ne_lines.py,sha256=kY_6ThigSc21ONyo38yq1gBhzlyUPYcfbYC50nIoiRs,64091
 DiadFit/relaxfi_PW.py,sha256=vXXW9JjEBRf0UR9p-DJLx8j4Z2ePpUDweoAok-2nMJ0,32119
 DiadFit/relaxifi.py,sha256=DSHAUP0tnkiMrHQgQPBK-9P3cWYmegURKzYOUgdAlos,38569
 DiadFit/smoothed_polyfit_June25_UCB.pkl,sha256=I_AHj8uJVv1lPfir6QZa-EmOzSp8yDAWUZH2ZTE-0KI,2596
-DiadFit-1.0.11.dist-info/LICENSE.txt,sha256=wM112Xn2cOj94pg0LUBgB-7Vs2y8KZ4bzrhIK-R72WE,1707
-DiadFit-1.0.11.dist-info/METADATA,sha256=kyVNmvm8Kx6fbPb-PsYKxFn8Byh1o2jhxoQMccqD0Bo,1172
-DiadFit-1.0.11.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-DiadFit-1.0.11.dist-info/top_level.txt,sha256=yZC6OFLVznaFA5kcPlFPkvhKotcVd-YO4bKxZZw3LQE,8
-DiadFit-1.0.11.dist-info/RECORD,,
+DiadFit-1.0.12.dist-info/LICENSE.txt,sha256=GzU7ouxObfYUKRAXOjoLZtZwb1fAZaiRDLmAz8puSeg,2308
+DiadFit-1.0.12.dist-info/METADATA,sha256=KmDlQB5Ch3o_vFzlauAFebYtOcGnvHfOk41FrDOesfo,1172
+DiadFit-1.0.12.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+DiadFit-1.0.12.dist-info/top_level.txt,sha256=yZC6OFLVznaFA5kcPlFPkvhKotcVd-YO4bKxZZw3LQE,8
+DiadFit-1.0.12.dist-info/RECORD,,