Skip to content
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.

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

⬆️ remove constraints on pandas and pytorch #51

Merged
merged 1 commit into from
Oct 11, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion project/00_0_0_lftp_upload_commands.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@
"metadata": {},
"outputs": [],
"source": [
"meta_stats = df_meta.describe(include='all', datetime_is_numeric=True)\n",
"meta_stats = df_meta.describe(include='all')\n",
"meta_stats.T"
]
},
Expand Down
2 changes: 1 addition & 1 deletion project/00_0_0_lftp_upload_commands.py
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ def rename(fname, new_sample_id, new_folder=None, ext=None):


# %%
meta_stats = df_meta.describe(include='all', datetime_is_numeric=True)
meta_stats = df_meta.describe(include='all')
meta_stats.T

# %% [markdown]
Expand Down
2 changes: 1 addition & 1 deletion project/00_0_hela_metadata_rawfiles.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -101,7 +101,7 @@
"metadata": {},
"outputs": [],
"source": [
"meta_stats = df_meta_rawfiles.describe(include='all', datetime_is_numeric=True)\n",
"meta_stats = df_meta_rawfiles.describe(include='all')\n",
"meta_stats.T"
]
},
Expand Down
2 changes: 1 addition & 1 deletion project/00_0_hela_metadata_rawfiles.py
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@
print(msg)

# %%
meta_stats = df_meta_rawfiles.describe(include='all', datetime_is_numeric=True)
meta_stats = df_meta_rawfiles.describe(include='all')
meta_stats.T

# %% [markdown]
Expand Down
2 changes: 1 addition & 1 deletion project/00_3_1_pride_metadata_analysis.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -177,7 +177,7 @@
"metadata": {},
"outputs": [],
"source": [
"meta_stats = df_meta.describe(include='all', datetime_is_numeric=True)\n",
"meta_stats = df_meta.describe(include='all')\n",
"meta_stats.T.to_excel(excel_writer, sheet_name='des_stats', **writer_args)\n",
"\n",
"view = meta_stats.loc[:, (meta_stats.loc['unique'] > 1)\n",
Expand Down
2 changes: 1 addition & 1 deletion project/00_3_1_pride_metadata_analysis.py
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,7 @@
# ## Varying data between runs

# %%
meta_stats = df_meta.describe(include='all', datetime_is_numeric=True)
meta_stats = df_meta.describe(include='all')
meta_stats.T.to_excel(excel_writer, sheet_name='des_stats', **writer_args)

view = meta_stats.loc[:, (meta_stats.loc['unique'] > 1)
Expand Down
7 changes: 3 additions & 4 deletions project/01_0_split_data.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -327,8 +327,7 @@
"metadata": {},
"outputs": [],
"source": [
"df_meta.describe(datetime_is_numeric=True,\n",
" percentiles=np.linspace(0.05, 0.95, 10))"
"df_meta.describe(percentiles=np.linspace(0.05, 0.95, 10))"
]
},
{
Expand Down Expand Up @@ -373,7 +372,7 @@
"metadata": {},
"outputs": [],
"source": [
"meta_stats = df_meta.describe(include='all', datetime_is_numeric=True)\n",
"meta_stats = df_meta.describe(include='all')\n",
"meta_stats"
]
},
Expand Down Expand Up @@ -697,7 +696,7 @@
"metadata": {},
"outputs": [],
"source": [
"pcs.describe(include='all', datetime_is_numeric=True).T"
"pcs.describe(include='all').T"
]
},
{
Expand Down
7 changes: 3 additions & 4 deletions project/01_0_split_data.py
Original file line number Diff line number Diff line change
Expand Up @@ -227,8 +227,7 @@ def join_as_str(seq):


# %%
df_meta.describe(datetime_is_numeric=True,
percentiles=np.linspace(0.05, 0.95, 10))
df_meta.describe(percentiles=np.linspace(0.05, 0.95, 10))

# %% [markdown]
# select samples with a minimum retention time
Expand All @@ -251,7 +250,7 @@ def join_as_str(seq):
df_meta = df_meta.sort_values(params.meta_date_col)

# %%
meta_stats = df_meta.describe(include='all', datetime_is_numeric=True)
meta_stats = df_meta.describe(include='all')
meta_stats

# %% [markdown]
Expand Down Expand Up @@ -434,7 +433,7 @@ def join_as_str(seq):
pcs

# %%
pcs.describe(include='all', datetime_is_numeric=True).T
pcs.describe(include='all').T

# %%
if params.meta_cat_col:
Expand Down
4 changes: 2 additions & 2 deletions setup.cfg
Original file line number Diff line number Diff line change
Expand Up @@ -22,9 +22,9 @@ include_package_data = True
install_requires =
numpy
matplotlib
pandas<2
pandas
plotly
torch<2
torch
scikit-learn>=1.0
scipy
seaborn
Expand Down
2 changes: 1 addition & 1 deletion vaep/pandas/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ def unique_cols(s: pd.Series) -> bool:


def show_columns_with_variation(df: pd.DataFrame) -> pd.DataFrame:
df_describe = df.describe(include='all', datetime_is_numeric=True)
df_describe = df.describe(include='all')
col_mask = (df_describe.loc['unique'] > 1) | (
df_describe.loc['std'] > 0.01)
return df.loc[:, col_mask]
Expand Down
Loading