ararpy 0.1.36__py3-none-any.whl → 0.1.37__py3-none-any.whl

ararpy/__init__.py

@@ -16,10 +16,10 @@ from . import calc, smp, files, thermo, test
 """ Information """
 
 name = 'ararpy'
-version = '0.1.36'
+version = '0.1.37'
 __version__ = version
 full_version = version
-last_update = '2025-12-08'
+last_update = '2025-12-12'
 
 """ ArArPy Functions """
 
@@ -141,6 +141,5 @@ RawData.get_sequence = smp.raw.get_sequence
 RawData.to_sample = smp.initial.from_raw_data
 RawData.get_unknown = lambda _raw: smp.raw.get_sequence(_raw, True, 'is_unknown', unique=False)
 RawData.get_blank = lambda _raw: smp.raw.get_sequence(_raw, True, 'is_blank', unique=False)
-RawData.get_air = lambda _raw: smp.raw.get_sequence(_raw, True, 'is_air', unique=False)
 Sequence.get_data_df = lambda _seq: pd.DataFrame(_seq.data)
 Sequence.get_flag_df = lambda _seq: pd.DataFrame(_seq.flag)

ararpy/calc/basic.py

@@ -57,6 +57,18 @@ def get_datetime(t_year: int, t_month: int, t_day: int, t_hour: int, t_min: int,
     return ts - base
 
 
+def get_timestring(timestamp: int = 0, base=None):
+    """
+    :param timestamp: timestamp (utz)
+    :param base: base time [y, m, d, h, m]
+    :return:
+    """
+    if base is None:
+        base = [1970, 1, 1, 0, 0]
+    ts = timestamp + datetime(*base, tzinfo=timezone.utc).timestamp()
+    return datetime.fromtimestamp(ts, tz=timezone.utc).isoformat(timespec='seconds')
+
+
 def merge_dicts(a: dict, b: dict):
     """
     a and b, two dictionary. Return updated a

ararpy/calc/regression.py

@@ -513,7 +513,7 @@ def linest(a0: list, a1: list, *args):
         args = [[1] * len(args[0]), *args]
         return [sum([beta[i] * args[i][j] for i in range(len(beta))]) for j in range(len(args[0]))]
 
-    return beta[0], se_beta[0], rse_beta[0] * 100, r2, m_ssresid, beta, se_beta, get_adjusted_y, m_ssresid
+    return beta[0], se_beta[0], abs(rse_beta[0]) * 100, r2, m_ssresid, beta, cov_beta, get_adjusted_y, m_ssresid
 
 
 def average(a0: list, a1=None):
@@ -538,12 +538,12 @@ def average(a0: list, a1=None):
     m_ssresid = ssresid / df
     r2 = ssreg / sstotal if sstotal != 0 else 1  # r2 = ssreg / sstotal
 
-    k1 = pow(sum([(i - k0) ** 2 for i in a0]) / df, 0.5)  # standard deviation
-    k2 = k1 / k0 * 100 if k0 != 0 else 0  # relative standard error
+    k6 = [[sum([(i - k0) ** 2 for i in a0]) / df]]
+    k1 = pow(k6[0][0], 0.5)  # standard deviation
+    k2 = k1 / abs(k0) * 100 if k0 != 0 else 0  # relative standard error
     k3 = r2  # determination coefficient
     k4 = m_ssresid  # 'MSWD'
     k5 = [k0]
-    k6 = [k1]
     k8 = m_ssresid
 
     def get_adjusted_y(x: list):
@@ -740,7 +740,7 @@ def quadratic(a0: list, a1: list):
     """
     # y = b + m1 * x + m2 * x ^ 2
     k = list(linest(a0, a1, [i ** 2 for i in a1]))
-    b, seb, rseb, r2, mswd, [b, m1, m2], [seb, sem1, sem2] = k[0:7]
+    [b, m1, m2] = k[5]
 
     def get_adjusted_y(x: list):
         return [b + m1 * _x + m2 * _x ** 2 for _x in x]
@@ -759,7 +759,7 @@ def polynomial(a0: list, a1: list, degree: int = 5):
     """
     # y = b + m1 * x + m2 * x ^ 2 + ... + m[n] * x ^ n
     k = list(linest(a0, *[[j ** (i + 1) for j in a1] for i in range(degree)]))
-    b, seb, rseb, r2, mswd, beta, se_beta = k[0:7]
+    beta = k[5]
 
     def get_adjusted_y(x: list):
         return [sum([beta[i] * _x ** i for i in range(degree + 1)]) for _x in x]
@@ -769,6 +769,7 @@ def polynomial(a0: list, a1: list, degree: int = 5):
     return k
 
 
+### Deprecated
 def logest(a0: list, a1: list):
     """
     :param a0: known_y's, y = b * m ^ x
@@ -778,15 +779,19 @@ def logest(a0: list, a1: list):
     # y = b * m ^ x, Microsoft Excel LOGEST function, ln(y) = ln(b) + ln(m) * x
     a0 = [np.log(i) for i in a0]  # ln(y)
     linest_res = linest(a0, a1)
-    lnb, selnb, rseb, r2, mswd, [lnb, lnm], [selnb, selnm] = linest_res[0:7]
+    lnb, selnb, rseb, r2, mswd, beta, cov_beta = linest_res[0:7]
+    lnb, lnm = beta
+    selnb, selnm = np.diagonal(cov_beta) ** .5
+
     b = np.exp(lnb)
     m = np.exp(lnm)
     sem = np.exp(lnm) * selnm
     seb = np.exp(lnb) * selnb  # Excel.Logest function do not consider the error propagation
-    rseb = seb / b * 100
+    rseb = seb / abs(b) * 100
     return b, seb, rseb, r2, mswd, m, sem
 
 
+### Deprecated
 def power(a0: list, a1: list):
     """
     :param a0: known_y's, y = a * x ^ b + c
@@ -844,7 +849,9 @@ def power(a0: list, a1: list):
         raise IndexError
 
     f = linest(a0, [_x ** b for _x in a1])
-    a, sea, c, sec = f[5][1], f[6][1], f[0], f[1]
+    beta, cov_beta = f[5:7]
+    c, a = beta
+    sec, sea = np.diagonal(cov_beta) ** .5
 
     calculated_y = [_pow_func(i, a, b, c) for i in a1]
     resid = [(calculated_y[i] - a0[i]) ** 2 for i in range(len(a0))]
@@ -865,13 +872,34 @@ def power(a0: list, a1: list):
     errfx = pow(sum([i ** 2 for i in a1]) / (dp * sum([i ** 2 for i in a1]) - sum(a1) ** 2), 0.5)
     # seb = errfz * sey = errfz * ssresid / df -> se_intercept = sey * errfx = seb / errfz * errfx
     se_intercept = sec / errfz * errfx
-    rse_intercept = se_intercept / intercept * 100
+    rse_intercept = se_intercept / abs(intercept) * 100
+
+
+    exp_beta = [a, b, c]
+    exp_cov_beta = [
+        [cov_beta[1][1], 0, cov_beta[1][0]],
+        [0,              0,              0],
+        [cov_beta[0][1], 0, cov_beta[0][0]],
+    ]
 
     return intercept, se_intercept, rse_intercept, r2, 'mswd', [a, b, c], 'se', \
            lambda x: [_pow_func(i, a, b, c) for i in x], m_ssresid
 
 
 def exponential(a0: list, a1: list):
+    try:
+        k = _exponential(a0, a1, newton_minimize_1d)
+        if k[2] > 100:
+            raise ValueError
+        if abs(k[0] - min(a0)) > 5 * (max(a0) - min(a0)):
+            raise ValueError
+    except Exception as e:
+        print(f"newton_minimize_1d failed, using grad minimize")
+        k = _exponential(a0, a1, grad_minimize)
+    return k
+
+
+def _exponential(a0, a1, method):
 
     X = np.array(a1)
     Y = np.array(a0)
@@ -894,21 +922,18 @@ def exponential(a0: list, a1: list):
         ssresid = sum(resid)
         return ssresid
 
+    # 1阶
+    ini_f1 = linest(Y, X)
+    y_range = max(Y) - min(Y)
+    ini_b = ini_f1[5][1] / max(y_range, 1e-12)
+    # 2阶
+    ini_f2 = quadratic(Y, X)
+    ini_b *= np.sign(ini_f1[5][1]) * np.sign(ini_f2[5][2])
 
-    ini_f = linest(np.log(Y), X)
-    ini_b = ini_f[5][1]
-
-    # 替换原来的 minimize_scalar 部分
-    try:
-        b, count = newton_minimize_1d(_get_s, x0=ini_b, h=1e-5, tol=1e-8, max_iter=30)
-    except Exception as e:
-        # 使用 scipy 一维优化
-        res = minimize_scalar(_get_s, bounds=(-2, 2), method='bounded', options={'xatol': 1e-8})
-        b, count = res.x, res.nfev
-
-    # print(f"{b = }, {count = }")
+    b, count = method(_get_s, ini_b)
 
     x = np.concatenate(([np.ones(len(a1))], [np.exp(b * np.array(a1))]), axis=0).transpose()
+
     m, n = x.shape  # number of data, number of unknown x
     try:
         inv_xtx = np.linalg.inv(np.matmul(x.transpose(), x))
@@ -932,11 +957,20 @@ def exponential(a0: list, a1: list):
     intercept = a + c
     se_intercept = pow(sa ** 2 + sc ** 2 + 2 * cov_beta[0][1] , 0.5)
 
-    return intercept, se_intercept, se_intercept / intercept * 100, r2, m_ssresid, [a, b, c], 'se', \
+    exp_beta = [a, b, c]
+    exp_cov_beta = [
+        [cov_beta[1][1], 0, cov_beta[1][0]],
+        [0,              0,              0],
+        [cov_beta[0][1], 0, cov_beta[0][0]],
+    ]
+
+    # print(f"{b = }, {a = }, {c = }, {count = }, {ssresid = }, {r2 = }")
+
+    return intercept, se_intercept, se_intercept / abs(intercept) * 100, r2, m_ssresid, exp_beta, exp_cov_beta, \
            lambda x: [_exp_func(xi, a, b, c) for xi in x], m_ssresid
 
 
-def newton_minimize_1d(func, x0, h=1e-5, tol=1e-8, max_iter=20):
+def newton_minimize_1d(func, x0, h=1e-5, tol=1e-8, max_iter=30):
     x = x0
     for i in range(max_iter):
         fx = func(x)
@@ -948,14 +982,12 @@ def newton_minimize_1d(func, x0, h=1e-5, tol=1e-8, max_iter=20):
         f_minus = func(x - h)
         if not (np.isfinite(f_plus) and np.isfinite(f_minus)):
             raise ValueError("Newton Minimize: Non-finite values in derivative computation")
-
         df = (f_plus - f_minus) / (2 * h)
         d2f = (f_plus - 2 * fx + f_minus) / (h * h)
 
         # 牛顿步长
         if abs(d2f) < 1e-12:  # 避免除零或平坦区域
-            print("Newton Minimize: Second derivative too small, stopping.")
-            break
+            raise ValueError("Newton Minimize: Second derivative too small, stopping.")
 
         step = df / d2f
         x_new = x - step
@@ -966,15 +998,51 @@ def newton_minimize_1d(func, x0, h=1e-5, tol=1e-8, max_iter=20):
 
         x = x_new
 
+    if i + 1 == max_iter:
+        raise ValueError("Newton Minimize: Over iteration max_iter={}".format(max_iter))
+
     return x, i + 1
 
+
+def grad_minimize(func, x, lr=1e-5, tol=1e-8, max_iter=1000):
+
+    for i in range(max_iter):
+        f_plus = func(x + lr)
+        f_minus = func(x - lr)
+        if not (np.isfinite(f_plus) and np.isfinite(f_minus)):
+            raise ValueError("Newton Minimize: Non-finite values in derivative computation")
+        g = (f_plus - f_minus) / (2 * lr)
+        x_new = x - lr * g
+        if abs(func(x_new) - func(x)) < tol:
+            break
+        x = x_new
+    return x, i+1
+
+
 """ line functions """
 
 
-def linear_eq(x: list, beta: list):
+def linest_var(beta: list, cov: list, x: float):
     """ y = b0 * x^0 + b1 * x^1 + ... + bn * x^n
     Parameters
     ----------
+
+    Returns
+    -------
+
+    """
+    beta = np.array(beta, dtype=np.float64)
+    cov_matrix = np.array(cov, dtype=np.float64)
+    g = np.array([x ** k for k in range(len(beta))]).reshape(-1, 1)
+    y = np.dot(g.T, beta.reshape(-1, 1))[0, 0]
+    var = np.matmul(np.matmul(g.T, cov_matrix), g)[0, 0]
+    return y, var
+
+
+def quadratic_var(beta: list, cov: list, x: float):
+    """ y = b0 * x^0 + b1 * x^1 + b2 * x^2
+    Parameters
+    ----------
     beta : coefficients
     x :
 
@@ -982,21 +1050,48 @@ def linear_eq(x: list, beta: list):
     -------
 
     """
-    return [np.prod([beta, [_x ** i for i in range(len(beta))]], axis=0).sum() for _x in x]
+    beta = np.array(beta, dtype=np.float64)
+    cov_matrix = np.array(cov, dtype=np.float64)
+    g = np.array([x ** k for k in range(len(beta))]).reshape(-1, 1)
+    y = np.dot(g.T, beta.reshape(-1, 1))[0, 0]
+    var = np.matmul(np.matmul(g.T, cov_matrix), g)[0, 0]
+    return y, var
 
 
-def exponential_eq(x: list, beta: list):
-    """ y = a * b ^ x + c
+def average_var(beta: list, cov: list, x: float):
+    """ y = b0 * x^0 + b1 * x^1 + ... + bn * x^n
     Parameters
     ----------
-    beta : coefficients, [a, b, c]
+    beta : coefficients
     x :
 
     Returns
     -------
 
     """
-    return [beta[0] * beta[1] ** _x + beta[0] for _x in x]
+    y, = beta
+    var = np.array(cov, dtype=np.float64)[0, 0]
+    return y, var
+
+
+def exponential_var(beta: list, cov: list, x: float):
+    """ y = a * exp(bx) + c
+    Parameters
+    ----------
+    beta : coefficients, [a, b, c]
+    cov : covariance [[], [], []]
+
+    Returns
+    -------
+
+    """
+    cov_matrix = np.array(cov)
+    a, b, c = beta
+    k = np.exp(b*x)
+    g = np.array([k, a*x*k, 1]).reshape(-1, 1)
+    y = a * k + c
+    var = np.matmul(np.matmul(g.T, cov_matrix), g)[0, 0]
+    return y, var
 
 
 def power_eq(x: list, beta: list):

ararpy/files/raw_file.py

@@ -212,7 +212,7 @@ def get_raw_data(file_contents: List[List[Union[int, float, str, bool, list]]],
         try:
             return datetime.strptime(string, f)
         except ValueError as v:
-            print(traceback.format_exc())
+            # print(traceback.format_exc())
             if f.strip() == "":
                 return datetime_parser.parse(string)
             elif len(v.args) > 0 and v.args[0].startswith('unconverted data remains: '):
@@ -229,8 +229,13 @@ def get_raw_data(file_contents: List[List[Union[int, float, str, bool, list]]],
         except (ValueError, TypeError):
             return s
 
+    def step_type_parse(s: str):
+        if any([s.lower().__contains__(each) for each in ['blk', 'blank']]):
+            return "Blank"
+        return "Unknown"
+
     step_list = []
-    idx = 0  # step_index
+    step_idx = 0  # step_index rows
 
     header = input_filter[5]
     isotope_index = input_filter[8:28]
@@ -242,7 +247,7 @@ def get_raw_data(file_contents: List[List[Union[int, float, str, bool, list]]],
     while True:  # measurment steps sloop
 
         # ============ all text information ============
-        options = get_sample_info(file_contents, optional_info_index, default="", base=[1, 1 - idx, 1])
+        options = get_sample_info(file_contents, optional_info_index, default="", base=[1, 1 - step_idx, 1])
 
         # ============ Step name ============
         try:
@@ -269,7 +274,7 @@ def get_raw_data(file_contents: List[List[Union[int, float, str, bool, list]]],
         # ============ Step information ============
         try:
             if check_box_index[2]:
-                string = get_item(file_contents, strings_index[1:4], default="", base=[1, 1 - idx, 1])
+                string = get_item(file_contents, strings_index[1:4], default="", base=[1, 1 - step_idx, 1])
                 res = string_parser(strings_index[4], string)
                 if res is not None:
                     options.update(dict(zip(DEFAULT_SAMPLE_INFO.keys(), [res.named.get(value, options.get(key)) for key, value in DEFAULT_SAMPLE_INFO.items()])))
@@ -304,6 +309,15 @@ def get_raw_data(file_contents: List[List[Union[int, float, str, bool, list]]],
             print(traceback.format_exc())
             raise ValueError(f"Failed to parse zero datetime: {e}")
             # zero_datetime = datetime(1970, 1, 1, 0, 0, 0).isoformat(timespec='seconds')
+
+        # ============== Step Type =============
+        step_type = step_type_parse(options.get("StepType"))  # blank or unknown
+        options.update({'StepType': step_type})
+
+        # ============== Step Type =============
+        exp_type = options.get("ExpType")  # crushing, laser, heating, air
+        options.update({'ExpType': exp_type})
+
         current_step = [[step_name, zero_datetime, options]]
 
         # ============ isotope data ============
@@ -317,9 +331,11 @@ def get_raw_data(file_contents: List[List[Union[int, float, str, bool, list]]],
                 break_num += 1
                 continue
             break_num = 0
-            if int(data_index[2]) == 0:  # == 0, vertical
-                start_row = data_index[24] * cycle_num + data_index[25] * cycle_num + header + idx
-                try:
+            try:
+                if int(data_index[2]) == 0:  # == 0, vertical
+                    start_row = data_index[24] * cycle_num + data_index[25] * cycle_num + header + step_idx
+                    if check_box_index[0] and start_row - step_idx - header >= data_index[28]:
+                        break
                     current_step.append([
                         str(cycle_num + 1),
                         # in sequence: Ar36, Ar37, Ar38, Ar39, Ar40
@@ -334,45 +350,38 @@ def get_raw_data(file_contents: List[List[Union[int, float, str, bool, list]]],
                         float(data_content[start_row + isotope_index[ 2] - base][isotope_index[ 3] - base]),
                         float(data_content[start_row + isotope_index[ 0] - base][isotope_index[ 1] - base]) * f,
                     ])
-                except (ValueError, IndexError):
-                    print(f"Cannot parse isotope data")
-                    print(traceback.format_exc())
-                    current_step.append([
-                        str(cycle_num + 1), None, None, None, None, None, None, None, None, None, None,
-                    ])
-            elif int(data_index[2]) == 1:  # == 1, horizontal
-                start_row = data_index[1] + idx
-                col_inc = data_index[24] * cycle_num + data_index[25] * cycle_num - base
-                try:
+                elif int(data_index[2]) == 1:  # == 1, horizontal
+                    start_row = data_index[1] + step_idx
+                    col_inc = data_index[24] * cycle_num + data_index[25] * cycle_num
                     current_step.append([
                         str(cycle_num + 1),
                         # Ar36, Ar37, Ar38, Ar39, Ar40
-                        float(data_content[start_row][isotope_index[19] + col_inc]),
-                        float(data_content[start_row][isotope_index[17] + col_inc]) * f,
-                        float(data_content[start_row][isotope_index[15] + col_inc]),
-                        float(data_content[start_row][isotope_index[13] + col_inc]) * f,
-                        float(data_content[start_row][isotope_index[11] + col_inc]),
-                        float(data_content[start_row][isotope_index[ 9] + col_inc]) * f,
-                        float(data_content[start_row][isotope_index[ 7] + col_inc]),
-                        float(data_content[start_row][isotope_index[ 5] + col_inc]) * f,
-                        float(data_content[start_row][isotope_index[ 3] + col_inc]),
-                        float(data_content[start_row][isotope_index[ 1] + col_inc]) * f,
+                        float(data_content[start_row][isotope_index[19] + col_inc - base]),
+                        float(data_content[start_row][isotope_index[17] + col_inc - base]) * f,
+                        float(data_content[start_row][isotope_index[15] + col_inc - base]),
+                        float(data_content[start_row][isotope_index[13] + col_inc - base]) * f,
+                        float(data_content[start_row][isotope_index[11] + col_inc - base]),
+                        float(data_content[start_row][isotope_index[ 9] + col_inc - base]) * f,
+                        float(data_content[start_row][isotope_index[ 7] + col_inc - base]),
+                        float(data_content[start_row][isotope_index[ 5] + col_inc - base]) * f,
+                        float(data_content[start_row][isotope_index[ 3] + col_inc - base]),
+                        float(data_content[start_row][isotope_index[ 1] + col_inc - base]) * f,
                     ])
-                except (ValueError, IndexError):
-                    print(f"Cannot parse isotope data")
-                    print(traceback.format_exc())
-                    current_step.append([
-                        str(cycle_num + 1), None, None, None, None, None, None, None, None, None, None,
-                    ])
-            else:
-                raise ValueError(f"{data_index[2]} not in [0, 1]")
+                else:
+                    raise ValueError(f"{data_index[2]} not in [0, 1]")
+            except Exception as e:
+                print(f"Cannot parse isotope data")
+                # print(traceback.format_exc())
+                current_step.append([
+                    str(cycle_num + 1), None, None, None, None, None, None, None, None, None, None,
+                ])
 
             cycle_num += 1
             if cycle_num >= data_index[3]:
                 break
 
         step_list.append(current_step)
-        idx = data_index[28] * len(step_list)
+        step_idx = data_index[28] * len(step_list)
         if not check_box_index[0] or len(step_list) >= 500:  # check_box_index[0]: multiple sequences
             # print(f"Multiple Sequence = {check_box_index[0]}, Step number = {len(step_list)}")
             break
@@ -398,39 +407,39 @@ def get_sample_info(file_contents: list, index_list: list, default="", base: Uni
     """
     sample_info = DEFAULT_SAMPLE_INFO.copy()
     sample_info.update({
-        "ExpName": get_item(file_contents, index_list[0:3], default=default, base=base),
-        "StepName": get_item(file_contents, index_list[3:6], default=default, base=base),
-        "StepType": get_item(file_contents, index_list[6:9], default=default, base=base),
-        "StepLabel": get_item(file_contents, index_list[9:12], default=default, base=base),
-        "ZeroYear": get_item(file_contents, index_list[12:15], default=default, base=base),
-        "ZeroHour": get_item(file_contents, index_list[15:18], default=default, base=base),
-        "ZeroMon": get_item(file_contents, index_list[18:21], default=default, base=base),
-        "ZeroMin": get_item(file_contents, index_list[21:24], default=default, base=base),
-        "ZeroDay": get_item(file_contents, index_list[24:27], default=default, base=base),
-        "ZeroSec": get_item(file_contents, index_list[27:30], default=default, base=base),
-        "SmpName": get_item(file_contents, index_list[30:33], default=default, base=base),
-        "SmpLoc": get_item(file_contents, index_list[33:36], default=default, base=base),
-        "SmpMatr": get_item(file_contents, index_list[36:39], default=default, base=base),
-        "ExpType": get_item(file_contents, index_list[39:42], default=default, base=base),
-        "SmpWeight": get_item(file_contents, index_list[42:45], default=default, base=base),
-        "Stepunit": get_item(file_contents, index_list[45:48], default=default, base=base),
-        "HeatingTime": get_item(file_contents, index_list[48:51], default=default, base=base),
-        "InstrName": get_item(file_contents, index_list[51:54], default=default, base=base),
-        "Researcher": get_item(file_contents, index_list[54:57], default=default, base=base),
-        "Analyst": get_item(file_contents, index_list[57:60], default=default, base=base),
-        "Lab": get_item(file_contents, index_list[60:63], default=default, base=base),
-        "Jv": get_item(file_contents, index_list[63:66], default=default, base=base),
-        "Jsig": get_item(file_contents, index_list[66:69], default=default, base=base),
-        "MDF": get_item(file_contents, index_list[69:72], default=default, base=base),
-        "MDFSig": get_item(file_contents, index_list[72:75], default=default, base=base),
-        "CalcName": get_item(file_contents, index_list[75:78], default=default, base=base),
-        "IrraName": get_item(file_contents, index_list[78:81], default=default, base=base),
-        "IrraLabel": get_item(file_contents, index_list[81:84], default=default, base=base),
-        "IrraPosH": get_item(file_contents, index_list[84:87], default=default, base=base),
-        "IrraPosX": get_item(file_contents, index_list[87:90], default=default, base=base),
-        "IrraPosY": get_item(file_contents, index_list[90:93], default=default, base=base),
-        "StdName": get_item(file_contents, index_list[93:96], default=default, base=base),
-        "StdAge": get_item(file_contents, index_list[96:99], default=default, base=base),
-        "StdAgeSig": get_item(file_contents, index_list[99:102], default=default, base=base),
+        "ExpName": get_item(file_contents, index_list[0:3], default=default, base=base).strip(),
+        "StepName": get_item(file_contents, index_list[3:6], default=default, base=base).strip(),
+        "StepType": get_item(file_contents, index_list[6:9], default=default, base=base).strip(),
+        "StepLabel": get_item(file_contents, index_list[9:12], default=default, base=base).strip(),
+        "ZeroYear": get_item(file_contents, index_list[12:15], default=default, base=base).strip(),
+        "ZeroHour": get_item(file_contents, index_list[15:18], default=default, base=base).strip(),
+        "ZeroMon": get_item(file_contents, index_list[18:21], default=default, base=base).strip(),
+        "ZeroMin": get_item(file_contents, index_list[21:24], default=default, base=base).strip(),
+        "ZeroDay": get_item(file_contents, index_list[24:27], default=default, base=base).strip(),
+        "ZeroSec": get_item(file_contents, index_list[27:30], default=default, base=base).strip(),
+        "SmpName": get_item(file_contents, index_list[30:33], default=default, base=base).strip(),
+        "SmpLoc": get_item(file_contents, index_list[33:36], default=default, base=base).strip(),
+        "SmpMatr": get_item(file_contents, index_list[36:39], default=default, base=base).strip(),
+        "ExpType": get_item(file_contents, index_list[39:42], default=default, base=base).strip(),
+        "SmpWeight": get_item(file_contents, index_list[42:45], default=default, base=base).strip(),
+        "Stepunit": get_item(file_contents, index_list[45:48], default=default, base=base).strip(),
+        "HeatingTime": get_item(file_contents, index_list[48:51], default=default, base=base).strip(),
+        "InstrName": get_item(file_contents, index_list[51:54], default=default, base=base).strip(),
+        "Researcher": get_item(file_contents, index_list[54:57], default=default, base=base).strip(),
+        "Analyst": get_item(file_contents, index_list[57:60], default=default, base=base).strip(),
+        "Lab": get_item(file_contents, index_list[60:63], default=default, base=base).strip(),
+        "Jv": get_item(file_contents, index_list[63:66], default=default, base=base).strip(),
+        "Jsig": get_item(file_contents, index_list[66:69], default=default, base=base).strip(),
+        "MDF": get_item(file_contents, index_list[69:72], default=default, base=base).strip(),
+        "MDFSig": get_item(file_contents, index_list[72:75], default=default, base=base).strip(),
+        "CalcName": get_item(file_contents, index_list[75:78], default=default, base=base).strip(),
+        "IrraName": get_item(file_contents, index_list[78:81], default=default, base=base).strip(),
+        "IrraLabel": get_item(file_contents, index_list[81:84], default=default, base=base).strip(),
+        "IrraPosH": get_item(file_contents, index_list[84:87], default=default, base=base).strip(),
+        "IrraPosX": get_item(file_contents, index_list[87:90], default=default, base=base).strip(),
+        "IrraPosY": get_item(file_contents, index_list[90:93], default=default, base=base).strip(),
+        "StdName": get_item(file_contents, index_list[93:96], default=default, base=base).strip(),
+        "StdAge": get_item(file_contents, index_list[96:99], default=default, base=base).strip(),
+        "StdAgeSig": get_item(file_contents, index_list[99:102], default=default, base=base).strip(),
     })
     return sample_info

ararpy/smp/info.py

@@ -15,9 +15,9 @@
 
 def name(smp, n: str = None):
     if n is None:
-        return smp.Info.sample.name
+        return smp.Info.experiment.name
     elif isinstance(n, str):
-        smp.Info.sample.name = n
+        smp.Info.experiment.name = n
         return n
     else:
         raise ValueError(f"{n} is not a string")

ararpy/smp/initial.py

@@ -140,15 +140,18 @@ def initial(smp: Sample):
     # Info
     setattr(smp, 'Info', ArArBasic(
         id='0', name='info', attr_name='Info', arr_version=samples.VERSION,
+        experiment=ArArBasic(
+            name='', type='', instrument='', mass_spec='', collectors='', step_num=0,
+        ),
         sample=ArArBasic(
             name='SAMPLE NAME', material='MATERIAL', location='LOCATION', type='Unknown', method='',
-            sequence_unit='', weight=''
+            sequence_unit='', weight='',
         ),
         researcher=ArArBasic(
-            name='RESEARCHER', addr='ADDRESS', email='EMAIL'
+            name='RESEARCHER', addr='ADDRESS', email='EMAIL',
         ),
         laboratory=ArArBasic(
-            name='LABORATORY', addr='ADDRESS', email='EMAIL', info='INFORMATION', analyst='ANALYST'
+            name='LABORATORY', addr='ADDRESS', email='EMAIL', info='INFORMATION', analyst='ANALYST',
         ),
         results=ArArBasic(
             name='RESULTS', plateau_F=[], plateau_age=[], total_F=[], total_age=[],
@@ -184,9 +187,9 @@ def initial(smp: Sample):
             name='REFERENCE', journal='JOURNAL', doi='DOI'
         ),
         preference=copy.deepcopy(PREFERENCE_RES),
-        experiment=ArArBasic(
-            name='', mass_spec='', collectors='', step_num=0
-        ),
+        irradiation= ArArBasic(
+            label='', pos_h='', pos_x='', pos_y='',
+        )
     ))
 
     decimal_places = PREFERENCE_RES['decimalPlaces']
@@ -472,14 +475,14 @@ def from_raw_data(raw: RawData, mapping: Optional[List[dict]] = None) -> Sample:
     for row in mapping:
         row_unknown_intercept = []
         row_blank_intercept = []
-
         unknown: Sequence = raw.get_sequence(row['unknown'], flag='name')
-        if row['blank'].lower() == "Interpolated Blank".lower():
+        try:
+            blank: Sequence = raw.get_sequence(row['blank'], flag='name')
+            if blank is None or blank == []: raise KeyError
+        except KeyError:
             blank: Sequence = arr.filter(
-                raw.interpolated_blank, func=lambda seq: seq.datetime == unknown.datetime,
+                raw.interpolated_blank, func=lambda seq: seq.datetime == unknown.datetime and seq.name == row['blank'],
                 get=None, unique=True)
-        else:
-            blank: Sequence = raw.get_sequence(row['blank'], flag='name')
         for i in range(5):
             row_unknown_intercept = arr.multi_append(row_unknown_intercept, *unknown.results[i][int(unknown.fitting_method[i])][:2])
             row_blank_intercept = arr.multi_append(row_blank_intercept, *blank.results[i][int(blank.fitting_method[i])][:2])

ararpy/smp/json.py

@@ -50,8 +50,8 @@ class MyEncoder(json.JSONEncoder):
                             Plot.Set, Plot.BasicAttr, RawData, Sequence, ArArBasic)):
             if isinstance(obj, Sequence):
                 return dict(obj.__dict__, **{
-                    'is_blank': obj.is_blank(), 'is_unknown': obj.is_unknown(),
-                    'is_air': obj.is_air()})
+                    'is_blank': obj.is_blank(), 'is_unknown': obj.is_unknown()
+                })
             return obj.__dict__
         # Error
         if isinstance(obj, BaseException):

ararpy/smp/raw.py

@@ -52,8 +52,9 @@ def to_raw(file_path: Union[str, List[str]], input_filter_path: Union[str, List[
         data = res.get('data', None)
         sequences = res.get('sequences', None)
         sequence_num = len(data) if data is not None else len(sequences)
+        experiment_name = data[0][0][2]['ExpName'] if data is not None else file_name
         fitting_method = [2, 0, 2, 2, 2]  # 0 - linear, 1 - quadratic, 2 - exponential, 3 - power, 4 - average
-        raw = RawData(name=file_name, data=data, isotopic_num=10, sequence_num=sequence_num, source=[file_path],
+        raw = RawData(name=experiment_name, data=data, isotopic_num=10, sequence_num=sequence_num, source=[file_path],
                       sequence=sequences, unit=str(input_filter[30]), fitting_method=[*fitting_method])
     else:
         raise ValueError("File path and input filter should be both string or list with a same length.")
@@ -152,11 +153,10 @@ def do_regression(raw: RawData, sequence_index: Optional[List] = None, isotopic_
         # unselected: list = [unselected[[isotopic_index*2 + 1, 2 * (isotopic_index + 1)]].dropna().values.tolist()
         #                     for isotopic_index in list(range(5))]
 
-        for index, isotope in enumerate(selected):
+        for index, isotopic_data in enumerate(selected):
             if hasattr(isotopic_index, '__getitem__') and index not in isotopic_index:
                 continue
-            # print(f"regression for {sequence.name = }, isotope {index = }")
-            res = raw_funcs.get_raw_data_regression_results(isotope)
+            res = raw_funcs.get_raw_data_regression_results(isotopic_data)
             try:
                 sequence.results[index] = res[1]
                 sequence.coefficients[index] = res[2]

ararpy/smp/sample.py

@@ -1177,9 +1177,7 @@ class Sequence:
     def as_type(self, type_str):
         if str(type_str).lower() in ["blk", "b", "blank"]:
             self.type_str = "blank"
-        if str(type_str).lower() in ["a", "air"]:
-            self.type_str = "air"
-        if self.type_str not in ["blank", "air"]:
+        else:
             self.type_str = "unknown"
 
     __as_type = as_type
@@ -1188,10 +1186,7 @@ class Sequence:
         return self.type_str == "blank"
 
     def is_unknown(self):
-        return self.type_str != "blank" and self.type_str != "air"
-
-    def is_air(self):
-        return self.type_str == "air"
+        return self.type_str != "blank"
 
     def as_blank(self):
         return self.as_type("blank")
@@ -1199,9 +1194,6 @@ class Sequence:
     def as_unknown(self):
         return self.as_type("unknown")
 
-    def as_air(self):
-        return self.as_type("air")
-
     def get_data_df(self):
         ...
 
@@ -1230,7 +1222,7 @@ class RawData:
         self.unit = unit
         self.isotopic_num = isotopic_num
         self.sequence_num = sequence_num
-        self.interpolated_blank = None
+        self.interpolated_blank = []
         if sequence is not None:
             self.sequence = sequence
         elif data is not None:
@@ -1241,7 +1233,7 @@ class RawData:
                     data=item[1:],
                     datetime=item[0][1],
                     fitting_method=[*kwargs.get("fitting_method", [0] * 5)],
-                    options=item[0][2]
+                    options=item[0][2],
                 ) for index, item in enumerate(data)]
         else:
             self.sequence: List[Sequence] = []
@@ -1275,8 +1267,5 @@ class RawData:
     def get_blank(self) -> Union[Sequence, List]:
         ...
 
-    def get_air(self) -> Union[Sequence, List]:
-        ...
-
     def to_sample(self, mapping: Optional[List[dict]]) -> Sample:
         ...

ararpy/smp/style.py

@@ -64,7 +64,10 @@ def set_plot_style(smp: Sample):
     # Auto position and contents of texts
     reset_text(smp)
     # Set title, which are deleted in initializing
-    suffix = f"{smp.Info.sample.name} {smp.Info.sample.material}"
+    exp_name = smp.Info.experiment.name
+    smp_name = smp.Info.sample.name
+    name = f"{exp_name} {smp_name}" if str(exp_name).lower().strip() != str(smp_name).lower().strip() else exp_name
+    suffix = f"{name} {smp.Info.sample.material}"
     for figure_id, figure in basic.get_components(smp).items():
         if isinstance(figure, Plot):
             if not hasattr(figure, 'title'):

{ararpy-0.1.36.dist-info → ararpy-0.1.37.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ararpy
-Version: 0.1.36
+Version: 0.1.37
 Summary: A project for Ar-Ar geochronology
 Home-page: https://github.com/wuyangchn/ararpy.git
 Author: Yang Wu

{ararpy-0.1.36.dist-info → ararpy-0.1.37.dist-info}/RECORD

@@ -5,12 +5,12 @@ ararpy/Example - Show MDD results.py,sha256=YFkiQual60lyCClsfvivr4REY6waSYuomf0u
 ararpy/Example - Show all Kfs age spectra.py,sha256=1edPtBpFfS0lC7vLnLu34mDHt_xjbc8ptk6rZ--pf-I,12304
 ararpy/Example - Show random walk results.py,sha256=8WWvbAI7ySiMR-XwtFe5kTQihW3mcqzL3S7EUZdoxYo,15477
 ararpy/Example - Tc calculation.py,sha256=sD9pu3IaZ8mBV95rV2wOEhlQUexFNqBUoBqnNMdUBis,19617
-ararpy/__init__.py,sha256=mVCcRD0R0FoAL0Q6u9paujSfaQ8YBP8A_FXELRXO5AI,6857
+ararpy/__init__.py,sha256=lguPXqCx66J1evLooyi_UF-O_dMUDWl4sH8z5VlpGns,6768
 ararpy/test.py,sha256=4F46-JJ1Ge12HGae0qO44Qc6kiEMHBgn2MsY_5LlHDo,3973
 ararpy/calc/__init__.py,sha256=kUjRuLE8TLuKOv3i976RnGJoEMj23QBZDu37LWs81U4,322
 ararpy/calc/age.py,sha256=WOZs70zXiBWDIEhXJLIaNiYTOFJNk0NDbH5e5zCbCks,5435
 ararpy/calc/arr.py,sha256=jD1Fd0Cj3xc7NqgnG4cp3VWQWxUlV0qCtPBZZokDG8o,15246
-ararpy/calc/basic.py,sha256=X8BoAjZgk52WfAbhOCUTEOkDIdSuz21gepN-Xke4oGA,4165
+ararpy/calc/basic.py,sha256=2Iqk5WBMH8hiOqW2cvyPNEAbGU7hoeGTQ08Y6mlyfv8,4550
 ararpy/calc/corr.py,sha256=QDitvLf6y5IBpHtVEJfOUVjWSlIP9qJ4Jhluk9eDEDE,18801
 ararpy/calc/err.py,sha256=63LtprqjemlIb1QGDst4Ggcv5KMSDHdlAIL-nyQs1eA,2691
 ararpy/calc/histogram.py,sha256=0GVbDdsjd91KQ1sa2B7NtZ4KGo0XpRIJapgIrzAwQUo,5777
@@ -18,7 +18,7 @@ ararpy/calc/isochron.py,sha256=ej9G2e68k6yszonWHsLcEubh3TA7eh1upTJP_X0ttAA,5726
 ararpy/calc/jvalue.py,sha256=OL5zPYU8Pac-wOxUWPCgu3onh2n01xDnhpi2mlUsjJM,1146
 ararpy/calc/plot.py,sha256=Hdtb-q18xYC8ZJeDKGRauCSbj4_7e6Z8HQs9aYgfvao,2139
 ararpy/calc/raw_funcs.py,sha256=Rza1nIBQCOlJK_X0XvzmJqNG_byuaZxotNbdM84M-gI,2736
-ararpy/calc/regression.py,sha256=3L6caRhAptWY7o3EGGk5sfB_C471crSUcwOQRrkLS7Q,40255
+ararpy/calc/regression.py,sha256=m2_xJAsQ7mBIbnrmxtSPIQapJH61jkxvXskxN-8f86k,42803
 ararpy/calc/spectra.py,sha256=_Q23eP9necHlaCoHf3_UfW1N3JmVZj5rcWFro8GS-CA,1995
 ararpy/examples/022_VU124-M11a.ahd,sha256=3m0Gd-ZObou3KsnRNFMf77QwzT1Uz3nu3vA33Sqeyng,5414
 ararpy/examples/20WHA0103.age,sha256=cT-a4d7Wt77aotx6v0G47vulY_TZIcZUcaVHB3pqTPM,380416
@@ -44,7 +44,7 @@ ararpy/files/arr_file.py,sha256=pD5MxkAydL7cNq2wmKFUaOU4jHhc3MzTYrwbxZ3f46w,881
 ararpy/files/basic.py,sha256=k2GXgZjhqSmKvpXQLjsXDksS_ZLvqD7AWW54fXnYvTI,1228
 ararpy/files/calc_file.py,sha256=bapIVd3QQBprdMdfxNbY8TJH1UkfphIUtim3ONypc3I,28779
 ararpy/files/new_file.py,sha256=efblARIBROVLWS2w3-98BxLX5VZ8grRpiTkJFtf_rAk,214
-ararpy/files/raw_file.py,sha256=IwU_1Urrk0FjOt3kUuOaYjBBFozhCVAdsP6STxRia-o,19778
+ararpy/files/raw_file.py,sha256=iaM53pUHD3-sIgrRA_jXNOn5KIdKxKLEur_0DxNVPLo,20445
 ararpy/files/xls.py,sha256=DVcZ_yRnc19p-m4leGGjt-YPDpSa2udYKmGyrM0qub0,640
 ararpy/smp/EXPORT_TO_PDF_DATA_PROPERTIES.py,sha256=baDM437tu6hsPv0uYfod0TREXlPd6kvMBFT1S9ZZlkk,3024
 ararpy/smp/__init__.py,sha256=k6_fa27UJsQK7K7oC5GYlwMo6l0Xd8af3QtOrZz2XJk,478
@@ -54,20 +54,20 @@ ararpy/smp/consts.py,sha256=XIdjdz8cYxspG2jMnoItdlUsxr3hKbNFJjMZJh1bpzw,393
 ararpy/smp/corr.py,sha256=U5K1Vld55IHea_fZ7EEY_8dkvjp0f6OhpdSxf7b9WGY,26551
 ararpy/smp/diffusion_funcs.py,sha256=NC5T0GYXCidgVqSy3BGmIroLWzQhyzYb5x4gg_L0dJ4,186694
 ararpy/smp/export.py,sha256=yAUlTvFBo2U703hZ79NlAcTYC7QZGXHUn_IRP7sQuRA,120638
-ararpy/smp/info.py,sha256=iKUELm-BuUduDlJKC1d8tKKNHbwwbNmhUg2pi6bcBvA,489
-ararpy/smp/initial.py,sha256=QGk7vh7JyVqalwnpd9VudQoX2Z9tyWzfIIw_cL5Sok0,18031
-ararpy/smp/json.py,sha256=BTZCjVN0aj9epc700nwkYEYMKN2lHBYo-pLmtnz5oHY,2300
+ararpy/smp/info.py,sha256=tpEIjrE4nR-GAYTricBk9gq0LuHh6F1Bt7HPo1rS2HM,497
+ararpy/smp/initial.py,sha256=4-ojO-_Dmuyt-W1Ueji3FYPSSAZrOZ2ZxyGxmar3Kn8,18203
+ararpy/smp/json.py,sha256=zfJCC_2LCDckqC8Fpu10jEA6Knl3UtKO31I5g4fvsBE,2273
 ararpy/smp/plots.py,sha256=fFuJxoFcnvGSysjdEdrbW_ITpukt0iGs2K25gshIKNU,33594
-ararpy/smp/raw.py,sha256=SeKaNZZRWjiE_7fMHwn1IgQxX17t8mNFYMnRiimMLRU,6474
-ararpy/smp/sample.py,sha256=HW2JIZZcNslYVQupAqlfLEKXBWdYol5Xpx0PDdPG44o,58905
-ararpy/smp/style.py,sha256=Q8f6SsqnxmzocxpZUyGDiNanVW0ijCZpxHKh19UIeoM,7800
+ararpy/smp/raw.py,sha256=77J1dEYL4ZSeftp4tyog_Cy1Y5bwHNaLqJK4i4KLOSY,6500
+ararpy/smp/sample.py,sha256=P3lh2kOThTGrtNNgPF02y6_9ORM6mAlMSwEsPxLQAwM,58566
+ararpy/smp/style.py,sha256=y0iQpN4jy3PGy31DG5-_P1fNFGgyUNdsJX9qlYGVMEM,7979
 ararpy/smp/table.py,sha256=Vq3GK9aslEuBhmvlQoUHjcs71Q6raSFYqd5veB1L9mk,6887
 ararpy/thermo/__init__.py,sha256=6VBuqTRFl403PVqOuMkVrut0nKaQsAosBmfW91X1dMg,263
 ararpy/thermo/arrhenius.py,sha256=Ass1ichHfqIAtpv8eLlgrUc1UOb3Urh1qzr1E3gLB4U,233
 ararpy/thermo/atomic_level_random_walk.py,sha256=ncw9DtxRfS6zlQbLVLNX7WNoO9sX_nSomwAsTH0_O3k,25910
 ararpy/thermo/basic.py,sha256=JJRZbYmvXlpRAV2FeFPwLhrig4ZhNQmJnWqgOjo-1YQ,11508
-ararpy-0.1.36.dist-info/licenses/LICENSE,sha256=cvG5t_C1qY_zUyJI7sNOa7gCArdngNPaOrfujl2LYuc,1085
-ararpy-0.1.36.dist-info/METADATA,sha256=z82ivzCqiDnDN8TjnGAk1EmL4-C_YLhhY99WFbLnw3Y,24516
-ararpy-0.1.36.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ararpy-0.1.36.dist-info/top_level.txt,sha256=9iTpsPCYuRYq09yQTk9d2lqB8JtTEOmbN-IcGB-K3vY,7
-ararpy-0.1.36.dist-info/RECORD,,
+ararpy-0.1.37.dist-info/licenses/LICENSE,sha256=cvG5t_C1qY_zUyJI7sNOa7gCArdngNPaOrfujl2LYuc,1085
+ararpy-0.1.37.dist-info/METADATA,sha256=CWUoNZxPs8oUAPXtcOFXxylMCwE21PMamMv_oEm-juM,24516
+ararpy-0.1.37.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ararpy-0.1.37.dist-info/top_level.txt,sha256=9iTpsPCYuRYq09yQTk9d2lqB8JtTEOmbN-IcGB-K3vY,7
+ararpy-0.1.37.dist-info/RECORD,,