Add Filmsense and Woollam file parsers

refellips/dataSE.py

@@ -4,6 +4,7 @@
 A basic representation of a 1D dataset
 """
 
+import copy
 import numpy as np
 import pandas as pd
 from refnx._lib import possibly_open_file
@@ -250,7 +251,7 @@ def refresh(self):
 
         """
         if self.filename is not None:
-            with open(self.filename) as f:
+            with possibly_open_file(self.filename) as f:
                 self.load(f)
 
 
@@ -496,7 +497,7 @@ def open_HORIBAfile(
     linenodict = {}
     MDingest = False
 
-    with open(fname, "r") as f:
+    with possibly_open_file(fname, "r") as f:
         lines = f.readlines()
 
         for i, line in enumerate(lines):
@@ -542,3 +543,353 @@ def open_HORIBAfile(
     data = [data_df["nm"], data_df["AOI"], data_df["Psi"], data_df["Delta"]]
 
     return DataSE(data, name=name, reflect_delta=reflect_delta, **metadata)
+
+
+def open_M2000file(fname, take_every=1, dropdatapoints=1):
+    """
+    Opens raw text files exported by Woolam's 'CompleteEASE' software.
+
+
+    Parameters
+    ----------
+    fname : file-handle or string
+        File to load the dataset from.
+
+    dropdatapoints : int
+        Includes every nth element from the woolam dataset in DataSE.
+        Use to speed up fitting for datasets where a narrow wavelength
+        resolution is not required.
+
+    take_every : int
+        For time-resolved data sets only. Includes every nth dataset in
+        the returned dictionary. Usefully for reducing the number of data
+        points that needs to be processed when you don't need high temporaral
+        resolution
+
+    Returns
+    ----------
+    datasets : DataSE structure or dict
+        If the file contains a single measurment, function returns
+        a single DataSE object containing wavelength, angle of
+        incidence, psi and delta.
+
+        If the file contains multiple measurements, such as a time-
+        series dataset, then it returns a dictionary containing
+        DataSE objects for each measurement point. The Dictionary
+        keys correspond to the measurement details (e.g., time in seconds).
+
+        Metadata contained within the file is stored in DataSE.metadata.
+    """
+
+    mode = None
+    metadata = {}
+
+    with possibly_open_file(fname, mode="r") as file:
+        file.readline()  # Skip the blank first line
+        firstline = file.readline()[:-1]
+        secondline = file.readline()[:-1]
+
+        if secondline == "nm":
+            mode = "single"
+            skiplines = 3
+        elif secondline == "Dynamic":
+            mode = "dynamic"
+            skiplines = 4
+        else:
+            raise ValueError(
+                "Currently, only single and time-series datasets can be read"
+            )
+
+    header = firstline[len("VASEmethod[") : -len("]")]
+    for ele in header.split(", "):
+        key, val = ele.split("=")
+        metadata[key] = val
+
+    if mode == "single":
+        return _open_M2000file_standard(
+            fname=fname,
+            dropdatapoints=dropdatapoints,
+            skiplines=skiplines,
+            metadata=metadata,
+        )
+    elif mode == "dynamic":
+        return _open_M2000file_kinetic(
+            fname=fname,
+            take_every=take_every,
+            dropdatapoints=dropdatapoints,
+            skiplines=skiplines,
+            metadata=metadata,
+        )
+
+
+def _open_M2000file_standard(fname, dropdatapoints=1, metadata={}, skiplines=3):
+    data = []
+    with possibly_open_file(fname, mode="r") as file:
+        for i in range(skiplines):
+            file.readline()
+
+        count = 0
+        while True:
+            data_row = []
+
+            count += 1
+
+            line = file.readline().split("\t")
+            if not line:
+                break
+            if len(line) == 1:
+                break
+            data_row.append(float(line[0]))  # Wavelength
+            data_row.append(float(line[1]))  # Angle
+            data_row.append(float(line[2]))  # Psi
+            data_row.append(float(line[3]))  # Delta
+            data_row.append(float(line[4]))  # Psi Error
+            data_row.append(float(line[5]))  # Delta Error
+
+            line = file.readline().split("\t")
+            data_row.append(float(line[2]))  # Unknown
+            data_row.append(float(line[3]))  # Depolarization %
+            data_row.append(float(line[4]))  # Unknown
+
+            line = file.readline().split("\t")
+            data_row.append(float(line[2]))  # Unknown
+            data_row.append(float(line[3]))  # Intensity
+            data_row.append(float(line[4]))  # Unknown
+
+            data.append(data_row)
+
+    data = np.array(data)
+    data = data[::dropdatapoints]
+    return DataSE(data[:, [0, 1, 2, 3]].T, **metadata)
+
+
+def _open_M2000file_kinetic(
+    fname, take_every=1, dropdatapoints=1, skiplines=4, metadata={}
+):
+    """
+    time in seconds
+    """
+    df = pd.read_csv(
+        fname,
+        skiprows=skiplines,
+        sep="\t",
+        names=[
+            "Wavelength, nm",
+            "Angle of incidence, ˚",
+            "Psi",
+            "Delta",
+            "Psi error",
+            "Delta error",
+            "None",
+            "Time, min",
+        ],
+    )
+
+    time_dict = {}
+    for idx, (time, subdf) in enumerate(df.groupby("Time, min")):
+        if idx % take_every == 0:
+            time_dict[np.round(time * 60, 1)] = DataSE(
+                np.array(
+                    [
+                        subdf["Wavelength, nm"],
+                        subdf["Angle of incidence, ˚"],
+                        subdf["Psi"],
+                        subdf["Delta"],
+                    ]
+                )[:, ::dropdatapoints],
+                **metadata,
+            )
+
+    return time_dict
+
+
+def open_FilmSenseFile(fname):
+    """
+    Opens text files exported from FilmSense ellipsometers.
+
+
+    Parameters
+    ----------
+    fname : file-handle or string
+        File to load the dataset from.
+
+    Returns
+    ----------
+    datasets : DataSE structure or dict
+        If the file contains a single measurment, function returns
+        a single DataSE object containing wavelength, angle of
+        incidence, psi and delta.
+
+        If the file contains multiple measurements, such as a time-
+        series dataset, then it returns a dictionary containing
+        DataSE objects for each measurement point. The Dictionary
+        keys correspond to the measurement details (e.g., time).
+
+        Metadata contained within the file is stored in DataSE.metadata.
+    """
+    with possibly_open_file(fname, "r") as f:
+        header = f.readline()
+        if header == "Film_Sense_Data\n":
+            return _open_FilmSenseFile_standard(f)
+        elif header == "Film_Sense_Dyn_Data\n":
+            return _open_FilmSenseFile_dynamic(f)
+        else:
+            assert False, "Filetype not recognized"
+
+
+def _parse_FilmSenseFileHeader(firstline, mode="standard"):
+    firstline = firstline[:-1]  # remove newline char
+    firstline = firstline.split("\t")
+
+    metadata = {
+        "numwvls": int(firstline[0]),
+        "numdatasets": int(firstline[1]),
+        "nomAOI": float(firstline[2]),
+    }
+
+    if mode == "standard":
+        metadata["AlignX"] = float(firstline[3])
+        metadata["AlignY"] = float(firstline[4])
+        metadata["AvInten"] = float(firstline[5])
+    elif mode == "dynamic":
+        metadata["?"] = float(firstline[3])
+    else:
+        assert False, "mode not recognized"
+
+    return metadata
+
+
+def _open_FilmSenseFile_standard(f):
+    """
+    Opens a single measurement captured by FS series
+    ellipsometers from filmsense. This function is designed to be
+    called by open_FilmSenseFile.
+    """
+    metadata = _parse_FilmSenseFileHeader(f.readline())
+
+    # Note - in the documentation the first numwvls lines are only supposed
+    # have 4 columns. In these data files they have 8.
+
+    df = pd.DataFrame(
+        columns=[
+            "Wavelength",
+            "led_Br",
+            "led_ExpL",
+            "led_ExpR",
+            "N",
+            "C",
+            "S",
+            "P",
+            "Intensity",
+            "Delta",
+            "Psi",
+        ],
+        index=np.linspace(
+            1, metadata["numwvls"], metadata["numwvls"], dtype=int
+        ),
+    )
+
+    for i in range(metadata["numwvls"]):
+        line = f.readline().split("\t")
+        df.loc[i + 1, "Wavelength"] = float(line[0])
+        df.loc[i + 1, "led_Br"] = float(line[1])
+        df.loc[i + 1, "led_ExpL"] = float(line[2])
+        df.loc[i + 1, "led_ExpR"] = float(line[3])
+
+    for i in range(metadata["numwvls"]):
+        line = f.readline().split("\t")
+        df.loc[i + 1, "N"] = float(line[0])
+        df.loc[i + 1, "C"] = float(line[1])
+        df.loc[i + 1, "S"] = float(line[2])
+        df.loc[i + 1, "P"] = float(line[3])
+        df.loc[i + 1, "Intensity"] = float(line[4])
+
+    S = np.array(df["S"], dtype=np.float32)
+    N = np.array(df["N"], dtype=np.float32)
+    C = np.array(df["C"], dtype=np.float32)
+    df["Psi"] = np.rad2deg(np.arccos(N) / 2)
+    # Delta1 = 180+np.rad2deg(np.arctan(np.array(df['S'], dtype=np.float32)/np.array(df['C'], dtype=np.float32)))
+
+    df["Delta"] = np.rad2deg(np.angle((C + 1j * S) / (1 + N)))
+
+    Psi = np.array(df["Psi"]).astype(np.float64)
+    Delta = np.array(df["Delta"]).astype(np.float64)
+
+    Deltamask = Delta < 0
+    Delta[Deltamask] = 360 + Delta[Deltamask]
+
+    AOI = np.ones_like(Psi) * metadata["nomAOI"]
+    Wvl = np.array(df["Wavelength"]).astype(np.float64)
+
+    return DataSE(data=[Wvl, AOI, Psi, Delta], reflect_delta=False, **metadata)
+
+
+def _open_FilmSenseFile_dynamic(f):
+    """
+    Opens dynamic (time resolved) data captured by FS series
+    ellipsometers from filmsense. This function is designed to be
+    called by open_FilmSenseFile.
+    """
+    metadata = _parse_FilmSenseFileHeader(f.readline(), mode="dynamic")
+
+    base_df = pd.DataFrame(
+        columns=[
+            "Wavelength",
+            "led_Br",
+            "led_ExpL",
+            "led_ExpR",
+            "N",
+            "C",
+            "S",
+            "P",
+            "Intensity",
+            "Delta",
+            "Psi",
+        ],
+        index=np.linspace(
+            1, metadata["numwvls"], metadata["numwvls"], dtype=int
+        ),
+    )
+
+    for i in range(metadata["numwvls"]):
+        line = f.readline().split("\t")
+        base_df.loc[i + 1, "Wavelength"] = float(line[0])
+        base_df.loc[i + 1, "led_Br"] = float(line[1])
+        base_df.loc[i + 1, "led_ExpL"] = float(line[2])
+        base_df.loc[i + 1, "led_ExpR"] = float(line[3])
+
+    f.readline()  # read header
+
+    time_series = {}
+    for i in range(metadata["numdatasets"]):
+        line = f.readline()[:-2]
+        line = line.split("\t")
+        time = float(line[0])
+        df = copy.deepcopy(base_df)
+
+        for j in range(metadata["numwvls"]):
+            J = j * 5
+            df.loc[j + 1, "N"] = float(line[J + 1])
+            df.loc[j + 1, "C"] = float(line[J + 2])
+            df.loc[j + 1, "S"] = float(line[J + 3])
+            df.loc[j + 1, "P"] = float(line[J + 4])
+            df.loc[j + 1, "Intensity"] = float(line[J + 5])
+
+        S = np.array(df["S"], dtype=np.float32)
+        N = np.array(df["N"], dtype=np.float32)
+        C = np.array(df["C"], dtype=np.float32)
+        df["Psi"] = np.rad2deg(np.arccos(N) / 2)
+        df["Delta"] = np.rad2deg(np.angle((C + 1j * S) / (1 + N)))
+
+        Psi = np.array(df["Psi"]).astype(np.float64)
+        Delta = np.array(df["Delta"]).astype(np.float64)
+        Deltamask = Delta < 0
+        Delta[Deltamask] = 360 + Delta[Deltamask]
+        AOI = np.ones_like(Psi) * metadata["nomAOI"]
+        Wvl = np.array(df["Wavelength"]).astype(np.float64)
+
+        time_series[time] = DataSE(
+            data=[Wvl, AOI, Psi, Delta], reflect_delta=False, **metadata
+        )
+
+    return time_series

refellips/tests/Filmsense_kineticTest.txt

@@ -0,0 +1,18 @@
+Film_Sense_Dyn_Data
+8	7	-70.012	2
+367.20	14.32	3.39	2.48	1.218	1.363	0.059
+449.64	16.00	6.05	7.27	1.453	1.634	-0.013
+525.63	26.05	4.72	2.96	1.275	1.154	-0.107
+593.58	14.23	6.64	4.04	1.273	1.046	-0.156
+656.32	17.51	6.78	3.84	1.265	0.971	-0.259
+732.22	25.33	6.58	3.26	1.263	1.171	-0.228
+852.88	23.45	5.67	3.48	1.008	0.929	-0.315
+946.73	25.09	3.51	4.97	0.645	0.916	-0.172
+Time	UV_N	UV_C	UV_S	UV_P	UV_I	Blue_N	Blue_C	Blue_S	Blue_P	Blue_I	Green_N	Green_C	Green_S	Green_P	Green_I	Yellow_N	Yellow_C	Yellow_S	Yellow_P	Yellow_I	Red_N	Red_C	Red_S	Red_P	Red_I	IR735_N	IR735_C	IR735_S	IR735_P	IR735_I	IR850_N	IR850_C	IR850_S	IR850_P	IR850_I	IR950_N	IR950_C	IR950_S	IR950_P	IR950_I	AlignX	AlignY	AveInt	Temp	TempSrc	Fit_Diff	Thick(nm).2
+4.953	0.58698	-0.69405	0.41683	0.99839	14.1911	0.84641	-0.50868	0.15761	0.99875	21.7871	0.90022	-0.41844	0.12045	0.99955	12.7409	0.92246	-0.37264	0.10105	0.99940	5.5965	0.93427	-0.34544	0.08841	0.99947	15.0567	0.94354	-0.32226	0.07666	0.99956	14.7487	0.95231	-0.29850	0.06330	1.00013	15.0186	0.95683	-0.28524	0.05574	0.99967	11.7999	-0.007	0.002	16.7077	30.72	33.938	0.0018764	3.2528
+14.858	0.58698	-0.69407	0.41679	0.99841	14.1889	0.84641	-0.50869	0.15758	0.99875	21.7858	0.90022	-0.41845	0.12043	0.99955	12.7369	0.92246	-0.37265	0.10103	0.99941	5.5882	0.93427	-0.34545	0.08839	0.99947	15.0501	0.94354	-0.32226	0.07664	0.99956	14.7373	0.95231	-0.29850	0.06329	1.00013	15.0115	0.95683	-0.28524	0.05573	0.99967	11.7931	-0.007	0.002	16.6965	30.72	33.969	0.001878	3.2517
+24.766	0.58675	-0.69342	0.41821	0.99841	14.1889	0.84630	-0.50851	0.15871	0.99875	21.7836	0.90015	-0.41834	0.12133	0.99955	12.7336	0.92241	-0.37256	0.10181	0.99942	5.5826	0.93422	-0.34538	0.08908	0.99947	15.0458	0.94351	-0.32221	0.07725	0.99956	14.7303	0.95228	-0.29847	0.06379	1.00013	15.0072	0.95682	-0.28521	0.05618	0.99967	11.7882	-0.007	0.002	16.6955	30.75	33.969	0.001874	3.2938
+34.663	0.58676	-0.69346	0.41812	0.99841	14.1883	0.84631	-0.50852	0.15863	0.99873	21.7835	0.90016	-0.41834	0.12128	0.99954	12.7327	0.92241	-0.37257	0.10174	0.99941	5.5801	0.93423	-0.34539	0.08903	0.99945	15.0444	0.94351	-0.32221	0.07721	0.99954	14.7268	0.95229	-0.29847	0.06376	1.00013	15.0051	0.95682	-0.28521	0.05615	0.99967	11.7849	-0.006	0.002	16.6952	30.72	34.000	0.0018767	3.2908
+44.570	0.58659	-0.69294	0.41922	0.99853	14.1755	0.84629	-0.50830	0.15944	0.99895	21.7754	0.90016	-0.41817	0.12186	0.99978	12.7226	0.92242	-0.37241	0.10220	0.99964	5.5743	0.93424	-0.34526	0.08940	0.99969	15.0367	0.94352	-0.32212	0.07751	0.99975	14.7155	0.95229	-0.29840	0.06399	1.00029	14.9982	0.95682	-0.28516	0.05635	0.99981	11.7744	-0.007	0.002	16.6919	30.72	33.969	0.0018933	3.3196
+54.475	0.58657	-0.69252	0.41994	0.99860	14.1648	0.84631	-0.50812	0.15994	0.99911	21.7735	0.90016	-0.41803	0.12230	0.99996	12.7178	0.92243	-0.37229	0.10260	0.99981	5.5718	0.93424	-0.34516	0.08977	0.99985	15.0339	0.94352	-0.32204	0.07786	0.99990	14.7093	0.95229	-0.29834	0.06429	1.00042	14.9935	0.95682	-0.28510	0.05662	0.99992	11.7640	-0.005	0.001	16.6822	30.72	33.938	0.0018738	3.3412
+64.379	0.58705	-0.69198	0.42017	0.99822	14.4094	0.84633	-0.50789	0.16053	0.99838	21.9729	0.90015	-0.41792	0.12280	0.99914	12.8851	0.92239	-0.37225	0.10307	0.99898	5.6434	0.93421	-0.34514	0.09021	0.99906	15.2389	0.94349	-0.32202	0.07827	0.99911	14.9515	0.95227	-0.29832	0.06464	0.99975	15.2378	0.95681	-0.28507	0.05692	0.99936	12.0183	0.017	0.021	16.9638	30.72	33.969	0.0017164	3.3601