Skip to content

io

Submodule handling the input/output operations.

load_pullf(pullf_files)

Load filenames and resturns them as list.

Filenames can be taken from file or glob them from globpattern.

Parameters:

  • pullf_files (Str) –

    file which contains pullf filenames or globpattern

Returns:

  • filenames ( (List[Str], Str1DArray) ) –

    list/array of filenames

Examples:

>>> from dcTMD.io import load_pullf
>>> # load filenames form file
>>> filenames = load_pullf('pullf_files.txt')
>>> # load filenames with glob pattern
>>> filenames = load_pullf('data/*.pullf.xvg')
Source code in src/dcTMD/io.py 
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
@beartype
def load_pullf(pullf_files: Str) -> (List[Str], Str1DArray):
    """Load filenames and resturns them as list.

    Filenames can be taken from file or glob them from globpattern.

    Parameters
    ----------
    pullf_files :
        file which contains `pullf` filenames or globpattern

    Returns
    -------
    filenames:
        list/array of filenames

    Examples
    --------
    >>> from dcTMD.io import load_pullf
    >>> # load filenames form file
    >>> filenames = load_pullf('pullf_files.txt')
    >>> # load filenames with glob pattern
    >>> filenames = load_pullf('data/*.pullf.xvg')
    """
    try:
        filenames = np.loadtxt(pullf_files, dtype='str')
    except FileNotFoundError as fnf_error:
        print(f'file {fnf_error} using glob.glob({pullf_files})')
        filenames = glob.glob(pullf_files)

    if not len(filenames):
        raise ValueError('No constraint force files found.')

    return filenames

write_output(out, estimator, filetype=('dat', 'npz'))

Take all calculated quantities and save them.

Parameters:

  • out (Str) –

    Output name. By default f'{out}_N{n_traj}'

  • estimator –

    Either a ForceEstimator or WorkEstimator instance.

  • filetype –

    Output filetype, either 'dat', 'npz' or both ('dat', 'npz').

Examples:

>>> from dcTMD.storing import load
>>> from dcTMD.io import write_output
>>> from dcTMD.dcTMD import WorkEstimator
>>> # Save the results from WorkEstimator
>>> # (ForceEstimator works similarly)
>>> # calculate dcTMD results from workset
>>> work = load('my_work_set')
>>> work_estimator = WorkEstimator(temperature=290.15)
>>> work_estimator.fit(work)
>>> out = 'my_dcTMD_results'
>>> # save results as 'npz' file
>>> write_output(out, work_estimator, filetype='npz')
>>> # results saves as 'my_dcTMD_results_N100.npz'
>>> # save results as 'dat' file
>>> write_output(out, work_estimator, filetype='dat')
>>> # save results as 'dat' and 'npz' file
>>> write_output(out, work_estimator, filetype=('dat', 'npz'))
Source code in src/dcTMD/io.py 
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
@beartype
def write_output(
    out: Str,
    estimator,
    filetype=('dat', 'npz'),
) -> None:
    """Take all calculated quantities and save them.

    Parameters
    ----------
    out :
        Output name. By default f'{out}_N{n_traj}'
    estimator :
        Either a ForceEstimator or WorkEstimator instance.
    filetype:
        Output filetype, either 'dat', 'npz' or both ('dat', 'npz').

    Examples
    --------
    >>> from dcTMD.storing import load
    >>> from dcTMD.io import write_output
    >>> from dcTMD.dcTMD import WorkEstimator
    >>> # Save the results from WorkEstimator
    >>> # (ForceEstimator works similarly)
    >>> # calculate dcTMD results from workset
    >>> work = load('my_work_set')
    >>> work_estimator = WorkEstimator(temperature=290.15)
    >>> work_estimator.fit(work)
    >>> out = 'my_dcTMD_results'
    >>> # save results as 'npz' file
    >>> write_output(out, work_estimator, filetype='npz')
    >>> # results saves as 'my_dcTMD_results_N100.npz'
    >>> # save results as 'dat' file
    >>> write_output(out, work_estimator, filetype='dat')
    >>> # save results as 'dat' and 'npz' file
    >>> write_output(out, work_estimator, filetype=('dat', 'npz'))
    """
    n_traj = len(estimator.names_)
    out = f'{out}_N{n_traj}'

    results_dict = {
        'x': estimator.position_,
        'Wmean': estimator.W_mean_,
        'Wdiss': estimator.W_diss_,
        'dG': estimator.dG_,
        'Gamma': estimator.friction_,
    }
    if hasattr(estimator, 's_dG_'):
        results_dict.update({
            's_W_mean': estimator.s_W_mean_,
            's_W_diss': estimator.s_W_diss_,
            's_dG': estimator.s_dG_,
        })
    if hasattr(estimator, 'friction_smooth_'):
        results_dict['Gamma_smooth'] = estimator.friction_smooth_
    if hasattr(estimator, 's_friction_'):
        results_dict['s_Gamma'] = estimator.s_friction_

    if 'dat' in filetype:
        header = list(results_dict.keys())
        arrays = np.vstack(list(results_dict.values()))
        print(f'save file {out}.dat')
        np.savetxt(
            f'{out}.dat',
            arrays.T,
            fmt='%20.8f',  # noqa: WPS323
            header='    '.join(header),
        )
    if 'npz' in filetype:
        print(f'save file {out}.npz')
        np.savez(
            f'{out}.npz',
            **results_dict,
        )

load_output(filepath)

Load file produced by write_output.

Parameters:

  • filepath (str) –

    Path to the .dat or .npz file to be loaded.

Returns:

  • Dict[str, Any] –

    A dictionary containing the loaded data. Keys correspond to the quantities saved in the .npz file, such as 'x', 'Wmean', 'Wdiss', 'dG', 'Gamma', and optionally 's_W_mean', 's_W_diss', 's_dG', 'Gamma_smooth', 's_Gamma' if they were present during saving.

Examples:

>>> from dcTMD.storing import load
>>> from dcTMD.io import write_output, load_output
>>> from dcTMD.dcTMD import WorkEstimator
>>> # Save the results from WorkEstimator
>>> work = load('my_work_set')
>>> work_estimator = WorkEstimator(temperature=290.15)
>>> work_estimator.fit(work)
>>> # save results as '.npz' file
>>> out = 'my_dcTMD_results'
>>> write_output(out, work_estimator, filetype='npz')
>>> # load results
>>> results = load_output('my_dcTMD_results_N100.npz')
>>> positions = results['x']
>>> mean_work = results['Wmean']
>>> dG = results['dG']
Source code in src/dcTMD/io.py 
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
@beartype
def load_output(filepath: str):
    """
    Load file produced by `write_output`.

    Parameters
    ----------
    filepath : str
        Path to the .dat or .npz file to be loaded.

    Returns
    -------
    Dict[str, Any]
        A dictionary containing the loaded data. Keys correspond to the
        quantities saved in the .npz file, such as 'x', 'Wmean', 'Wdiss',
        'dG', 'Gamma', and optionally 's_W_mean', 's_W_diss', 's_dG',
        'Gamma_smooth', 's_Gamma' if they were present during saving.

    Examples
    --------
    >>> from dcTMD.storing import load
    >>> from dcTMD.io import write_output, load_output
    >>> from dcTMD.dcTMD import WorkEstimator
    >>> # Save the results from WorkEstimator
    >>> work = load('my_work_set')
    >>> work_estimator = WorkEstimator(temperature=290.15)
    >>> work_estimator.fit(work)
    >>> # save results as '.npz' file
    >>> out = 'my_dcTMD_results'
    >>> write_output(out, work_estimator, filetype='npz')
    >>> # load results
    >>> results = load_output('my_dcTMD_results_N100.npz')
    >>> positions = results['x']
    >>> mean_work = results['Wmean']
    >>> dG = results['dG']
    """
    if not Path(filepath).is_file():
        raise FileNotFoundError(
            f'The file "{filepath}" does not exist.',
        )
    if '.npz' in filepath:
        with np.load(filepath) as npzfile:
            res_dict = {key: npzfile[key] for key in npzfile.files}
        print(f'Loaded data from {filepath}')
        return res_dict
    elif '.dat' in filepath:
        with open(filepath, 'r') as datfile:
            # Read the header line, which starts with '#'
            for line in datfile:
                if line.startswith('#', 0, 5):
                    headers = line.split()
                    headers.remove('#')
                    break
        dctmd_results = np.loadtxt(filepath)
        res_dict = {}
        for idx, key in enumerate(headers):
            res_dict[key] = dctmd_results[:, idx]
        print(f'Loaded data from {filepath}')
        return res_dict
    else:
        print('Could not load file.')
        print(f'{filepath} needs to be .dat or .npz file.')