Added read_fwf based implementation for AME.

Author: soham

src/pynch/ame.py

@@ -0,0 +1,95 @@
+import numpy as np
+import pandas as pd
+
+from nuclearmasses.ame_formats import AME_MASS_FORMAT, AME_RCT1_FORMAT, AME_RCT2_FORMAT
+from nuclearmasses.parser import ELEMENTS, FWFParser
+
+AME_YEARS = [1993, 1995, 2003, 2012, 2016, 2020]
+
+
+class AMEMassParser(FWFParser):
+    """Parses AME mass files."""
+
+    def __init__(self, year: int):
+        if year not in AME_YEARS:
+            raise ValueError(f"You must choose a year from {AME_YEARS}.")
+        self.year = year
+
+    def _colspecs(self) -> dict[str, tuple[int, int]]:
+        if self.year == 2020:
+            return AME_MASS_FORMAT["2020"]
+        if 2003 <= self.year <= 2016:
+            return AME_MASS_FORMAT["2003"]
+        if self.year <= 1995:
+            return AME_MASS_FORMAT["1993"]
+
+    def _filespecs(self) -> dict[str, int]:
+        if self.year == 2020:
+            return {"header": 35, "footer": 0}
+        if 2003 <= self.year <= 2016:
+            return {"header": 38, "footer": 0}
+        if self.year <= 1995:
+            return {"header": 39, "footer": 0}
+
+    def _sanitize_data(self, df: pd.DataFrame) -> pd.DataFrame:
+        to_float = [
+            col for col in df.columns if col not in ["Z", "A", "BetaDecayChannel"]
+        ]
+        for col in to_float:
+            if "Error" not in col:
+                df[col + "Extrapolated"] = df[col].str.endswith("#")
+        df = df.replace("#", ".0", regex=True)
+        df = df.replace("*", np.nan)
+        df["AtomicMass"] = df["AtomicMass"].replace(" ", "", regex=True)
+        df[to_float] = df[to_float].apply(pd.to_numeric)
+        if self.year <= 1995:
+            df["BindingEnergyPerNucleon"] = df["BindingEnergy"] / df["A"]
+            df["BindingEnergyPerNucleonError"] = df["BindingEnergyError"] / df["A"]
+
+        df["N"] = df["A"] - df["Z"]
+        df["Element"] = [ELEMENTS[z] for z in df["Z"]]
+        df["TableYear"] = self.year
+
+        return df
+
+
+class AMEReactionParser(FWFParser):
+    """Parses AME reaction files."""
+
+    def __init__(self, year: int, rct: int):
+        if year not in AME_YEARS:
+            raise ValueError(f"You must choose a year from {AME_YEARS}.")
+        self.year = year
+        if rct != 1 and rct != 2:
+            raise ValueError("rct must be either 1 or 2.")
+        self.rct = rct
+        self.rct_format = AME_RCT1_FORMAT if self.rct == 1 else AME_RCT2_FORMAT
+
+    def _colspecs(self) -> dict[str, tuple[int, int]]:
+        if self.year == 2020:
+            return self.rct_format["2020"]
+        if self.year < 2020:
+            return self.rct_format["1993"]
+
+    def _filespecs(self) -> dict[str, int]:
+        if self.year == 2020:
+            header = 35 if self.rct == 1 else 37
+            footer = 0 if self.rct == 1 else 15
+            return {"header": header, "footer": footer}
+        if self.year < 2020:
+            return {"header": 39, "footer": 0}
+
+    def _sanitize_data(self, df: pd.DataFrame) -> pd.DataFrame:
+        to_float = [col for col in df.columns if col not in ["Z", "A"]]
+        for col in to_float:
+            if "Error" not in col:
+                df[col + "Extrapolated"] = df[col].str.endswith("#")
+        df = df.replace("#", ".0", regex=True)
+        df = df.replace("*", np.nan)
+        df[to_float] = df[to_float].apply(pd.to_numeric)
+
+        df["N"] = df["A"] - df["Z"]
+        df["Element"] = [ELEMENTS[z] for z in df["Z"]]
+        df["TableYear"] = self.year
+
+        return df

src/pynch/ame_formats.py

@@ -0,0 +1,111 @@
+AME_MASS_FORMAT = {
+    "2020": {
+        "Z": (9, 14),
+        "A": (14, 19),
+        "MassExcess": (28, 42),
+        "MassExcessError": (42, 54),
+        "BindingEnergyPerNucleon": (54, 67),
+        "BindingEnergyPerNucleonError": (68, 78),
+        "BetaDecayChannel": (78, 81),
+        "BetaDecayEnergy": (81, 94),
+        "BetaDecayEnergyError": (94, 105),
+        "AtomicMass": (106, 123),
+        "AtomicMassError": (123, -1),
+    },
+    "2003": {
+        "Z": (9, 14),
+        "A": (14, 19),
+        "MassExcess": (29, 41),
+        "MassExcessError": (42, 53),
+        "BindingEnergyPerNucleon": (54, 64),
+        "BindingEnergyPerNucleonError": (65, 72),
+        "BetaDecayChannel": (72, 76),
+        "BetaDecayEnergy": (76, 86),
+        "BetaDecayEnergyError": (87, 95),
+        "AtomicMass": (96, 112),
+        "AtomicMassError": (113, -1),
+    },
+    "1993": {
+        "Z": (10, 14),
+        "A": (14, 19),
+        "MassExcess": (29, 39),
+        "MassExcessError": (40, 48),
+        "BindingEnergy": (48, 60),
+        "BindingEnergyError": (60, 69),
+        "BetaDecayChannel": (72, 75),
+        "BetaDecayEnergy": (75, 85),
+        "BetaDecayEnergyError": (86, 94),
+        "AtomicMass": (97, 110),
+        "AtomicMassError": (111, -1),
+    },
+}
+
+AME_RCT1_FORMAT = {
+    "2020": {
+        "Z": (8, 11),
+        "A": (1, 4),
+        "TwoNeutronSeparationEnergy": (14, 24),
+        "TwoNeutronSeparationEnergyError": (25, 34),
+        "TwoProtonSeparationEnergy": (36, 46),
+        "TwoProtonSeparationEnergyError": (47, 56),
+        "QAlpha": (58, 68),
+        "QAlphaError": (69, 78),
+        "QTwoBeta": (79, 90),
+        "QTwoBetaError": (91, 100),
+        "QEpsilon": (101, 112),
+        "QEpsilonError": (113, 122),
+        "QBetaNeutron": (123, 134),
+        "QBetaNeutronError": (135, -1),
+    },
+    "1993": {
+        "Z": (8, 11),
+        "A": (1, 4),
+        "TwoNeutronSeparationEnergy": (14, 22),
+        "TwoNeutronSeparationEnergyError": (22, 30),
+        "TwoProtonSeparationEnergy": (32, 40),
+        "TwoProtonSeparationEnergyError": (41, 48),
+        "QAlpha": (49, 58),
+        "QAlphaError": (59, 66),
+        "QTwoBeta": (67, 76),
+        "QTwoBetaError": (77, 84),
+        "QEpsilon": (85, 94),
+        "QEpsilonError": (95, 102),
+        "QBetaNeutron": (103, 112),
+        "QBetaNeutronError": (113, -1),
+    },
+}
+
+AME_RCT2_FORMAT = {
+    "2020": {
+        "Z": (8, 11),
+        "A": (1, 4),
+        "OneNeutronSeparationEnergy": (14, 24),
+        "OneNeutronSeparationEnergyError": (25, 34),
+        "OneProtonSeparationEnergy": (36, 46),
+        "OneProtonSeparationEnergyError": (47, 56),
+        "QFourBeta": (57, 68),
+        "QFourBetaError": (69, 78),
+        "QDeuteronAlpha": (79, 90),
+        "QDeuteronAlphaError": (91, 100),
+        "QProtonAlpha": (101, 112),
+        "QProtonAlphaError": (113, 122),
+        "QNeutronAlpha": (123, 134),
+        "QNeutronAlphaError": (135, -1),
+    },
+    "1993": {
+        "Z": (8, 11),
+        "A": (1, 4),
+        "OneNeutronSeparationEnergy": (14, 22),
+        "OneNeutronSeparationEnergyError": (23, 30),
+        "OneProtonSeparationEnergy": (32, 40),
+        "OneProtonSeparationEnergyError": (41, 48),
+        "QFourBeta": (49, 58),
+        "QFourBetaError": (59, 66),
+        "QDeuteronAlpha": (67, 76),
+        "QDeuteronAlphaError": (77, 84),
+        "QProtonAlpha": (85, 94),
+        "QProtonAlphaError": (95, 102),
+        "QNeutronAlpha": (103, 112),
+        "QNeutronAlphaError": (113, -1),
+    },
+}