class PerovskitesDiffusionRester(MPContribsRester):
"""PerovskitesDiffusion-specific convenience functions to interact with MPContribs REST interface"""
mpfile = MPFile.from_file(os.path.join(
os.path.dirname(__file__), '..', 'mpfile_init.txt'
))
query = {'content.doi': mpfile.hdata.general['doi']}
provenance_keys = [k for k in mpfile.hdata.general.keys() if k != 'google_sheet']
def get_contributions(self):
docs = self.query_contributions(
projection={'_id': 1, 'mp_cat_id': 1, 'content.data': 1, 'content.abbreviations': 1}
)
if not docs:
raise Exception('No contributions found for PerovskitesDiffusion Explorer!')
data, columns = [], None
for doc in docs:
mpfile = MPFile.from_contribution(doc)
mp_id = mpfile.ids[0]
contrib = mpfile.hdata[mp_id]['data']
cid_url = self.get_cid_url(doc)
if columns is None:
columns = ['mp-id', 'contribution'] + contrib.keys()
row = [mp_id, cid_url] + contrib.values()
data.append((mp_id, row))
return Table.from_items(data, orient='index', columns=columns)
def get_abbreviations(self):
return self.get_global_hierarchical_data(['abbreviations']).get('abbreviations')
class MpWorkshop2017Rester(MPContribsRester):
"""MpWorkshop2017-specific convenience functions to interact with MPContribs REST interface"""
mpfile = MPFile.from_file(os.path.join(
os.path.dirname(__file__), '..', 'mpfile_init.txt'
))
query = {'content.source': mpfile.hdata.general['source']}
provenance_keys = [k for k in mpfile.hdata.general.keys() if k != 'google_sheet']
def get_contributions(self):
docs = self.query_contributions(
projection={'_id': 1, 'mp_cat_id': 1, 'content.data': 1}
)
if not docs:
raise Exception('No contributions found for MpWorkshop2017 Explorer!')
data = []
columns = ['mp-id', 'contribution']
for doc in docs:
mpfile = MPFile.from_contribution(doc)
mp_id = mpfile.ids[0]
contrib = mpfile.hdata[mp_id]['data']
cid_url = self.get_cid_url(doc)
for k in contrib.keys():
if k not in columns:
columns.append(k)
row = [mp_id, cid_url]
for col in columns[2:]:
row.append(contrib.get(col, ''))
data.append([mp_id, row])
# enforce equal row lengths
ncols = len(columns)
for entry in data:
n = len(entry[1])
if n != ncols:
entry[1] += [''] * (ncols - n)
return Table.from_items(data, orient='index', columns=columns)
def get_graphs(self):
docs = self.query_contributions(
projection={'_id': 1, 'mp_cat_id': 1, 'content': 1}
)
if not docs:
raise Exception('No contributions found for MpWorkshop2017 Explorer!')
graphs = {}
for doc in docs:
mpfile = MPFile.from_contribution(doc)
mp_id = mpfile.ids[0]
graphs[mp_id] = mpfile.gdata[mp_id]
return graphs
class SwfRester(MPContribsRester):
"""SWF-specific convenience functions to interact with MPContribs REST interface"""
mpfile = MPFile.from_file(
os.path.join(os.path.dirname(__file__), '..', 'mpfile_init.txt'))
query = {'content.doi': mpfile.hdata.general['doi']}
provenance_keys = [
k for k in mpfile.hdata.general.keys() if k != 'google_sheet'
]
def get_contributions(self):
docs = self.query_contributions(projection={
'_id': 1,
'mp_cat_id': 1,
'content.data': 1
})
if not docs:
raise Exception('No contributions found for SWF Explorer!')
data = []
columns = ['formula', 'contribution']
for doc in docs:
mpfile = MPFile.from_contribution(doc)
formula = mpfile.ids[0]
contrib = mpfile.hdata[formula].get('data')
if contrib is None:
continue
cid_url = self.get_cid_url(doc)
for k in contrib.keys():
if k not in columns:
columns.append(k)
row = [formula, cid_url]
for col in columns[2:]:
row.append(contrib.get(col, ''))
data.append([formula, row])
# enforce equal row lengths
ncols = len(columns)
for entry in data:
n = len(entry[1])
if n != ncols:
entry[1] += [''] * (ncols - n)
return Table.from_items(data, orient='index', columns=columns)
] + ["Hop attempt frequency, v_X [THz]"]
df_v = df[["Solute element name"] + columns_v]
df_v.columns = ["Solute"] + ["vₐ [THz]"] + ["vₓ [THz]"]
mpfile.add_data_table(mpid, df_v, "hop_attempt_frequencies")
print("DONE")
mpfile = MPFile()
mpfile.max_contribs = 15
run(mpfile)
print(mpfile)
filename = f"{project}.txt"
mpfile.write_file(filename=filename)
mpfile = MPFile.from_file(filename)
print(len(mpfile.ids))
table_names = ["D₀_Q", "hop_activation_barriers", "hop_attempt_frequencies"]
for idx, (identifier, content) in enumerate(mpfile.document.items()):
# doc = {'identifier': identifier, 'project': project, 'content': {}}
# doc['content']['data'] = content['data']
# doc['collaborators'] = [{'name': 'Patrick Huck', 'email': '*****@*****.**'}]
# r = db.contributions.insert_one(doc)
# cid = r.inserted_id
# print(idx, ':', cid)
# tids = []
# for name in table_names:
# table = mpfile.document[identifier][name]
import sys, json, os
from pympler import asizeof
if __name__ == '__main__':
if not os.path.exists('martin_lab.json'):
from mpcontribs.users.martin_lab.pre_submission import run
from mpcontribs.io.archieml.mpfile import MPFile
from mpcontribs.rest.adapter import ContributionMongoAdapter
from mpcontribs.builder import MPContributionsBuilder, export_notebook
mpfile = MPFile.from_file('MPContribs/mpcontribs/users/martin_lab/mpfile_init.txt')
run(mpfile)
cma = ContributionMongoAdapter()
for mpfile_single in mpfile.split():
contributor = 'Patrick Huck <*****@*****.**>'
doc = cma.submit_contribution(mpfile_single, contributor)
cid = doc['_id']
print doc.keys()
mcb = MPContributionsBuilder(doc)
build_doc = mcb.build(contributor, cid)
nb = build_doc[-1]
print nb.keys()
with open('martin_lab.json', 'w') as f:
json.dump(nb, f)
print 'DONE'
with open('martin_lab.json', 'r') as f:
nb = json.load(f)
for idx, cell in enumerate(nb['cells']):
if idx: # skip first cell
import sys, json, os
from pympler import asizeof
if not os.path.exists('martin_lab.json'):
from mpcontribs.users.martin_lab.pre_submission import run
from mpcontribs.io.archieml.mpfile import MPFile
from mpcontribs.rest.adapter import ContributionMongoAdapter
from mpcontribs.builder import MPContributionsBuilder, export_notebook
mpfile = MPFile.from_file('MPContribs/mpcontribs/users/martin_lab/mpfile_init.txt')
run(mpfile)
cma = ContributionMongoAdapter()
for mpfile_single in mpfile.split():
contributor = 'Patrick Huck <*****@*****.**>'
doc = cma.submit_contribution(mpfile_single, contributor)
cid = doc['_id']
print doc.keys()
mcb = MPContributionsBuilder(doc)
build_doc = mcb.build(contributor, cid)
nb = build_doc[-1]
print nb.keys()
with open('martin_lab.json', 'w') as f:
json.dump(nb, f)
print 'DONE'
with open('martin_lab.json', 'r') as f:
nb = json.load(f)
for idx, cell in enumerate(nb['cells']):
if idx: # skip first cell
obj_size = asizeof.asizeof(cell) / 1024. / 1024.
if obj_size > 1.:
import argparse, os
from mpcontribs.io.archieml.mpfile import MPFile
from pre_submission import *
parser = argparse.ArgumentParser(
description="""generate MPFile from directory of related XAS measurements"""
)
parser.add_argument('-i',
'--input_mpfile',
type=str,
metavar="PATH",
help="""path to input
MPFile with shared MetaData and processing instructions for each
composition""",
default="input.txt")
parser.add_argument('-o',
'--output_mpfile',
type=str,
metavar="FILENAME",
help="""name of
output MPFile with shared MetaData and processing results for each
composition (will be created in same directory as `input_mpfile`)""",
default="output.txt")
args = parser.parse_args()
mpfile = MPFile.from_file(args.input_mpfile)
run(mpfile)
work_dir = os.path.dirname(os.path.realpath(args.input_mpfile))
output_mpfile = os.path.join(work_dir, args.output_mpfile)
mpfile.write_file(output_mpfile)
import argparse, os
from mpcontribs.io.archieml.mpfile import MPFile
from pre_submission import *
parser = argparse.ArgumentParser(
description="""generate MPFile from directory of related XAS measurements"""
)
parser.add_argument(
'-i', '--input_mpfile', type=str, metavar="PATH", help="""path to input
MPFile with shared MetaData and processing instructions for each
composition""", default="input.txt"
)
parser.add_argument(
'-o', '--output_mpfile', type=str, metavar="FILENAME", help="""name of
output MPFile with shared MetaData and processing results for each
composition (will be created in same directory as `input_mpfile`)""",
default="output.txt"
)
args = parser.parse_args()
mpfile = MPFile.from_file(args.input_mpfile)
run(mpfile)
work_dir = os.path.dirname(os.path.realpath(args.input_mpfile))
output_mpfile = os.path.join(work_dir, args.output_mpfile)
mpfile.write_file(output_mpfile)
elif "rev_dB_p3" in name:
offset = 4.49694000e-10
elif "fwd_dG_p6" in name:
offset = -8.90037000e-11
elif "rev_dG_p6" in name:
offset = 8.42196000e-10
temp = name[4:].split("CZnO", 1)[0]
direction = "fwd" if "fwd" in name else "rev"
col = ycol.format(temp, direction)
full_df[col] = (df[ycol] + offset).abs() * 1000.0 / 0.045
mpfile.add_data_table(identifier, full_df, "JV|dark")
mpfile = MPFile.from_file("mpfile_init.txt")
mpfile.max_contribs = 2
run(mpfile)
print(mpfile)
filename = f"{project}.txt"
mpfile.write_file(filename=filename)
mpfile = MPFile.from_file(filename)
print(len(mpfile.ids))
mpfile.document.pop("_hdata")
for idx, (identifier, content) in enumerate(mpfile.document.items()):
doc = {"identifier": identifier, "project": project, "content": {}}
doc["content"]["data"] = content.pop("data")
doc["collaborators"] = [{"name": "Patrick Huck", "email": "*****@*****.**"}]
def test_get_string():
test_file = os.path.join(os.path.dirname(__file__), 'test_archieml.txt')
mpfile = MPFile.from_file(test_file)
mpfile_test = MPFile.from_string(mpfile.get_string())
assert mpfile.document == mpfile_test.document
def test_get_string():
mpfile = MPFile.from_file('test_files/test_archieml.txt')
mpfile_test = MPFile.from_string(mpfile.get_string())
assert_equal(mpfile.document, mpfile_test.document)
def test_get_string():
mpfile = MPFile.from_file('test_files/test_archieml.txt')
mpfile_test = MPFile.from_string(mpfile.get_string())
assert_equal(mpfile.document, mpfile_test.document)
