Skip to content

Use to_parquet instead of depricated msgpack #91

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
lakodarmstadt wants to merge 4 commits into from
Closed

Use to_parquet instead of depricated msgpack #91

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
2447f67
Use to_parquet to save dataframe
Feb 24, 2021
8bbee7f
rename file ending .ftr to .parquet
lakodarmstadt Feb 25, 2021
39121a7
bugfix load_dataframe
lakodarmstadt Mar 16, 2021
b252312
bugfix: Hide add_shots_progress-bar when loading dataframe
Mar 16, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 8 additions & 9 deletions lyse/__main__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1602,7 +1602,7 @@ def add_files(self, filepaths, new_row_data, done=False):
# Update the Qt model:
for filepath in to_add:
self.update_row(filepath, dataframe_already_updated=True)
app.filebox.set_add_shots_progress(None, None, None)

@inmain_decorator()
def get_first_incomplete(self):
Expand Down Expand Up @@ -2243,23 +2243,23 @@ def on_save_dataframe_triggered(self, choose_folder=True):
for sequence in sequences:
sequence_df = pandas.DataFrame(df[df['sequence'] == sequence], columns=df.columns).dropna(axis=1, how='all')
labscript = sequence_df['labscript'].iloc[0]
filename = "dataframe_{}_{}.msg".format(sequence.to_pydatetime().strftime("%Y%m%dT%H%M%S"),labscript[:-3])
filename = "dataframe_{}_{}.parquet".format(sequence.to_pydatetime().strftime("%Y%m%dT%H%M%S"),labscript[:-3])
if not choose_folder:
save_path = os.path.dirname(sequence_df['filepath'].iloc[0])
sequence_df.infer_objects()
for col in sequence_df.columns :
if sequence_df[col].dtype == object:
sequence_df[col] = pandas.to_numeric(sequence_df[col], errors='ignore')
sequence_df.to_msgpack(os.path.join(save_path, filename))
sequence_df.to_parquet(os.path.join(save_path, filename))
else:
error_dialog('Dataframe is empty')

def on_load_dataframe_triggered(self):
default = os.path.join(self.exp_config.get('paths', 'experiment_shot_storage'), 'dataframe.msg')
default = os.path.join(self.exp_config.get('paths', 'experiment_shot_storage'), 'dataframe.parquet')
file = QtWidgets.QFileDialog.getOpenFileName(self.ui,
'Select dataframe file to load',
default,
"dataframe files (*.msg)")
"dataframe files (*.parquet)")
if type(file) is tuple:
file, _ = file
if not file:
Expand All @@ -2268,8 +2268,8 @@ def on_load_dataframe_triggered(self):
# Convert to standard platform specific path, otherwise Qt likes
# forward slashes:
file = os.path.abspath(file)
df = pandas.read_msgpack(file).sort_values("run time").reset_index()
df = pandas.read_parquet(file).sort_values("run time").reset_index()

# Check for changes in the shot files since the dataframe was exported
def changed_since(filepath, time):
if os.path.isfile(filepath):
Expand All @@ -2279,9 +2279,8 @@ def changed_since(filepath, time):

filepaths = df["filepath"].tolist()
changetime_cache = os.path.getmtime(file)
need_updating = np.where(map(lambda x: changed_since(x, changetime_cache), filepaths))[0]
need_updating = np.where(list(map(lambda x: changed_since(x, changetime_cache), filepaths)))[0]
need_updating = np.sort(need_updating)[::-1] # sort in descending order to not remove the wrong items with pop

# Reload the files where changes where made since exporting
for index in need_updating:
filepath = filepaths.pop(index)
Expand Down