🎨🔥 use combine_value_counts from njab

project/10_4_ald_compare_single_pg.ipynb

@@ -18,19 +18,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import logging\n",
     "from pathlib import Path\n",
     "\n",
-    "import logging\n",
+    "import matplotlib\n",
     "import matplotlib.pyplot as plt\n",
+    "import njab\n",
     "import pandas as pd\n",
-    "\n",
-    "import matplotlib\n",
     "import seaborn\n",
     "\n",
     "import vaep\n",
     "import vaep.analyzers\n",
-    "import vaep.io.datasplits\n",
     "import vaep.imputation\n",
+    "import vaep.io.datasplits\n",
     "\n",
     "logger = vaep.logging.setup_nb_logger()\n",
     "logging.getLogger('fontTools').setLevel(logging.WARNING)\n",
@@ -251,8 +251,7 @@
     "fname = args.out_folder / 'equality_rejected_target.pkl'\n",
     "files_out[fname.name] = fname.as_posix()\n",
     "da_target.to_pickle(fname)\n",
-    "\n",
-    "count_rejected = vaep.pandas.combine_value_counts(da_target.droplevel(-1, axis=1))\n",
+    "count_rejected = njab.pandas.combine_value_counts(da_target.droplevel(-1, axis=1))\n",
     "count_rejected.to_excel(writer, sheet_name='count_rejected')\n",
     "count_rejected"
    ]
@@ -264,10 +263,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! This uses implicitly that RSN is not available for some protein groups\n",
-    "! Make an explicit list of the 313 protein groups available in original data\n",
+    "# ! This uses implicitly that RSN is not available for some protein groups\n",
+    "# ! Make an explicit list of the 313 protein groups available in original data\n",
     "mask_common = da_target.notna().all(axis=1)\n",
-    "count_rejected_common = vaep.pandas.combine_value_counts(da_target.loc[mask_common].droplevel(-1, axis=1))\n",
+    "count_rejected_common = njab.pandas.combine_value_counts(da_target.loc[mask_common].droplevel(-1, axis=1))\n",
     "count_rejected_common.to_excel(writer, sheet_name='count_rejected_common')\n",
     "count_rejected_common"
    ]
@@ -276,12 +275,10 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "af1a13cb",
-   "metadata": {
-    "lines_to_next_cell": 2
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "count_rejected_new = vaep.pandas.combine_value_counts(da_target.loc[~mask_common].droplevel(-1, axis=1))\n",
+    "count_rejected_new = njab.pandas.combine_value_counts(da_target.loc[~mask_common].droplevel(-1, axis=1))\n",
     "count_rejected_new.to_excel(writer, sheet_name='count_rejected_new')\n",
     "count_rejected_new"
    ]

project/10_4_ald_compare_single_pg.py

@@ -19,19 +19,19 @@
 # - dumps top5
 
 # %%
+import logging
 from pathlib import Path
 
-import logging
+import matplotlib
 import matplotlib.pyplot as plt
+import njab
 import pandas as pd
-
-import matplotlib
 import seaborn
 
 import vaep
 import vaep.analyzers
-import vaep.io.datasplits
 import vaep.imputation
+import vaep.io.datasplits
 
 logger = vaep.logging.setup_nb_logger()
 logging.getLogger('fontTools').setLevel(logging.WARNING)
@@ -153,25 +153,23 @@
 fname = args.out_folder / 'equality_rejected_target.pkl'
 files_out[fname.name] = fname.as_posix()
 da_target.to_pickle(fname)
-
-count_rejected = vaep.pandas.combine_value_counts(da_target.droplevel(-1, axis=1))
+count_rejected = njab.pandas.combine_value_counts(da_target.droplevel(-1, axis=1))
 count_rejected.to_excel(writer, sheet_name='count_rejected')
 count_rejected
 
 # %%
-# ! This uses implicitly that RSN is not available for some protein groups
-# ! Make an explicit list of the 313 protein groups available in original data
+# # ! This uses implicitly that RSN is not available for some protein groups
+# # ! Make an explicit list of the 313 protein groups available in original data
 mask_common = da_target.notna().all(axis=1)
-count_rejected_common = vaep.pandas.combine_value_counts(da_target.loc[mask_common].droplevel(-1, axis=1))
+count_rejected_common = njab.pandas.combine_value_counts(da_target.loc[mask_common].droplevel(-1, axis=1))
 count_rejected_common.to_excel(writer, sheet_name='count_rejected_common')
 count_rejected_common
 
 # %%
-count_rejected_new = vaep.pandas.combine_value_counts(da_target.loc[~mask_common].droplevel(-1, axis=1))
+count_rejected_new = njab.pandas.combine_value_counts(da_target.loc[~mask_common].droplevel(-1, axis=1))
 count_rejected_new.to_excel(writer, sheet_name='count_rejected_new')
 count_rejected_new
 
-
 # %%
 da_target.to_excel(writer, sheet_name='equality_rejected_all')
 da_target

project/10_5_comp_diff_analysis_repetitions.ipynb

@@ -8,7 +8,10 @@
    "outputs": [],
    "source": [
     "from pathlib import Path\n",
+    "\n",
+    "import njab\n",
     "import pandas as pd\n",
+    "\n",
     "import vaep"
    ]
   },
@@ -333,7 +336,7 @@
     "mask_new_da_with_imp = mask_new_da_with_imputation = ((~mask_pgs_included_in_ald_study)\n",
     "                                                      & (da_counts['None'] != 10))\n",
     "\n",
-    "tab_new_da_with_imp = vaep.pandas.combine_value_counts(\n",
+    "tab_new_da_with_imp = njab.pandas.combine_value_counts(\n",
     "    da_counts\n",
     "    .loc[mask_new_da_with_imputation]\n",
     ").fillna(0).astype(int)\n",

project/10_5_comp_diff_analysis_repetitions.py

@@ -14,7 +14,10 @@
 
 # %%
 from pathlib import Path
+
+import njab
 import pandas as pd
+
 import vaep
 
 # %%
@@ -176,7 +179,7 @@ def _load_pickle(pfath, run: int):
 mask_new_da_with_imp = mask_new_da_with_imputation = ((~mask_pgs_included_in_ald_study)
                                                       & (da_counts['None'] != 10))
 
-tab_new_da_with_imp = vaep.pandas.combine_value_counts(
+tab_new_da_with_imp = njab.pandas.combine_value_counts(
     da_counts
     .loc[mask_new_da_with_imputation]
 ).fillna(0).astype(int)

project/10_7_ald_reduced_dataset_plots.ipynb

@@ -16,10 +16,13 @@
    "outputs": [],
    "source": [
     "from pathlib import Path\n",
+    "\n",
     "import matplotlib.pyplot as plt\n",
+    "import njab\n",
     "import pandas as pd\n",
     "\n",
     "import vaep\n",
+    "\n",
     "plt.rcParams['figure.figsize'] = [4, 2]  # [16.0, 7.0] , [4, 3]\n",
     "vaep.plotting.make_large_descriptors(6)\n",
     "\n",
@@ -79,14 +82,15 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "676766a0",
-   "metadata": {},
+   "metadata": {
+    "lines_to_next_cell": 2
+   },
    "outputs": [],
    "source": [
     "files_out = dict()\n",
     "fname = out_folder / 'ald_reduced_dataset_plots.xlsx'\n",
     "files_out[fname.name] = fname.as_posix()\n",
-    "writer = pd.ExcelWriter(fname)\n",
-    "\n"
+    "writer = pd.ExcelWriter(fname)"
    ]
   },
   {
@@ -237,7 +241,7 @@
     "     1: 'TP'}\n",
     ").droplevel(-1, axis=1)\n",
     ")\n",
-    "da_target_sel_counts = vaep.pandas.combine_value_counts(da_target_sel_counts)\n",
+    "da_target_sel_counts = njab.pandas.combine_value_counts(da_target_sel_counts)\n",
     "ax = da_target_sel_counts.T.plot.bar(ylabel='count')\n",
     "ax.locator_params(axis='y', integer=True)\n",
     "fname = out_folder / 'lost_signal_da_counts.pdf'\n",
@@ -308,7 +312,7 @@
     "     1: 'FP'}\n",
     ").droplevel(-1, axis=1)\n",
     ")\n",
-    "da_target_sel_counts = vaep.pandas.combine_value_counts(da_target_sel_counts)\n",
+    "da_target_sel_counts = njab.pandas.combine_value_counts(da_target_sel_counts)\n",
     "ax = da_target_sel_counts.T.plot.bar(ylabel='count')\n",
     "ax.locator_params(axis='y', integer=True)\n",
     "fname = out_folder / 'gained_signal_da_counts.pdf'\n",

project/10_7_ald_reduced_dataset_plots.py

@@ -3,10 +3,13 @@
 
 # %%
 from pathlib import Path
+
 import matplotlib.pyplot as plt
+import njab
 import pandas as pd
 
 import vaep
+
 plt.rcParams['figure.figsize'] = [4, 2]  # [16.0, 7.0] , [4, 3]
 vaep.plotting.make_large_descriptors(6)
 
@@ -54,7 +57,6 @@ def plot_qvalues(df, x: str, y: list, ax=None, cutoff=0.05,
 writer = pd.ExcelWriter(fname)
 
 
-
 # %%
 
 
@@ -124,7 +126,7 @@ def plot_qvalues(df, x: str, y: list, ax=None, cutoff=0.05,
      1: 'TP'}
 ).droplevel(-1, axis=1)
 )
-da_target_sel_counts = vaep.pandas.combine_value_counts(da_target_sel_counts)
+da_target_sel_counts = njab.pandas.combine_value_counts(da_target_sel_counts)
 ax = da_target_sel_counts.T.plot.bar(ylabel='count')
 ax.locator_params(axis='y', integer=True)
 fname = out_folder / 'lost_signal_da_counts.pdf'
@@ -168,7 +170,7 @@ def plot_qvalues(df, x: str, y: list, ax=None, cutoff=0.05,
      1: 'FP'}
 ).droplevel(-1, axis=1)
 )
-da_target_sel_counts = vaep.pandas.combine_value_counts(da_target_sel_counts)
+da_target_sel_counts = njab.pandas.combine_value_counts(da_target_sel_counts)
 ax = da_target_sel_counts.T.plot.bar(ylabel='count')
 ax.locator_params(axis='y', integer=True)
 fname = out_folder / 'gained_signal_da_counts.pdf'

vaep/pandas/__init__.py

@@ -1,45 +1,15 @@
 import collections.abc
 from collections import namedtuple
-
-
 from types import SimpleNamespace
-
 from typing import Iterable
 
 import numpy as np
-import pandas as pd
 import omegaconf
+import pandas as pd
 
 from .calc_errors import calc_errors_per_feat, get_absolute_error
 
 
-def combine_value_counts(X: pd.DataFrame, dropna=True) -> pd.DataFrame:
-    """Pass a selection of columns to combine it's value counts.
-
-    This performs no checks. Make sure the scale of the variables
-    you pass is comparable.
-
-    Parameters
-    ----------
-    X : pandas.DataFrame
-        A DataFrame of several columns with values in a similar range.
-    dropna : bool, optional
-        Exclude NA values from counting, by default True
-
-    Returns
-    -------
-    pandas.DataFrame
-        DataFrame of combined value counts.
-    """
-    """
-    """
-    _df = pd.DataFrame()
-    for col in X.columns:
-        _df = _df.join(X[col].value_counts(dropna=dropna), how='outer')
-    freq_targets = _df.sort_index()
-    return freq_targets
-
-
 def unique_cols(s: pd.Series) -> bool:
     """Check all entries are equal in pandas.Series