data-manipulation-utilities 0.2.7__py3-none-any.whl → 0.2.8.dev720__py3-none-any.whl

dmu/ml/cv_predict.py

@@ -1,8 +1,6 @@
 '''
 Module holding CVPredict class
 '''
-from typing import Optional
-
 import pandas as pnd
 import numpy
 import tqdm
@@ -21,41 +19,107 @@ class CVPredict:
     Class used to get classification probabilities from ROOT
     dataframe and a set of models. The models were trained with CVClassifier
     '''
-    def __init__(self, models : Optional[list] = None, rdf : Optional[RDataFrame] = None):
+    def __init__(
+            self,
+            rdf    : RDataFrame,
+            models : list[CVClassifier]):
         '''
         Will take a list of CVClassifier models and a ROOT dataframe
-        '''
-
-        if models is None:
-            raise ValueError('No list of models passed')
-
-        if rdf is None:
-            raise ValueError('No ROOT dataframe passed')
 
+        rdf   : ROOT dataframe where features will be extracted
+        models: List of models, one per fold
+        '''
         self._l_model   = models
         self._rdf       = rdf
+        self._nrows     : int
+        self._l_column  : list[str]
         self._d_nan_rep : dict[str,str]
 
-        self._arr_patch : numpy.ndarray
+        # Value of score used when no score has been assigned
+        self._dummy_score = -1.0
+
+        # name of column in ROOT dataframe where 1s will prevent prediction
+        self._skip_index_column = 'skip_mva_prediction'
+
+        # name of attribute of features dataframe where array of indices to skip are stored
+        self._index_skip  = 'skip_mva_prediction'
     # --------------------------------------------
     def _initialize(self):
+        self._rdf       = self._remove_periods(self._rdf)
         self._rdf       = self._define_columns(self._rdf)
         self._d_nan_rep = self._get_nan_replacements()
+        self._l_column  = [ name.c_str() for name in self._rdf.GetColumnNames() ]
+        self._nrows     = self._rdf.Count().GetValue()
+    # ----------------------------------
+    def _remove_periods(self, rdf : RDataFrame) -> RDataFrame:
+        '''
+        This will redefine all columns associated to friend trees as:
+
+        friend_preffix.branch_name -> friend_preffix.branch_name
+        '''
+        l_col = [ col.c_str() for col in rdf.GetColumnNames() ]
+        l_col = [ col         for col in l_col if '.' in col  ]
+
+        if len(l_col) == 0:
+            return rdf
+
+        log.debug(60 * '-')
+        log.debug('Renaming dotted columns')
+        log.debug(60 * '-')
+        for col in l_col:
+            new = col.replace('.', '_')
+            log.debug(f'{col:<50}{"->":10}{new:<20}')
+            rdf = rdf.Define(new, col)
+
+        return rdf
+    # --------------------------------------------
+    def _get_definitions(self) -> dict[str,str]:
+        '''
+        This method will search in the configuration the definitions used
+        on the dataframe before the dataframe was used to train the model.
+        '''
+        cfg   = self._l_model[0].cfg
+        d_def = {}
+        if 'define' in cfg['dataset']:
+            d_def_gen = cfg['dataset']['define'] # get generic definitions
+            d_def.update(d_def_gen)
+
+        sig_name = 'sig'
+        try:
+            # Get sample specific definitions. This will be taken from the signal section
+            # because predicted scores should come from features defined as for the signal.
+            d_def_sam = cfg['dataset']['samples'][sig_name]['definitions']
+        except KeyError:
+            log.debug(f'No sample specific definitions were found in: {sig_name}')
+            return d_def
+
+        log.info('Adding sample dependent definitions')
+        d_def.update(d_def_sam)
+
+        return d_def
     # --------------------------------------------
     def _define_columns(self, rdf : RDataFrame) -> RDataFrame:
-        cfg = self._l_model[0].cfg
-
-        if 'define' not in cfg['dataset']:
-            log.debug('No define section found in config, will not define extra columns')
+        d_def = self._get_definitions()
+        if len(d_def) == 0:
+            log.info('No definitions found')
             return self._rdf
 
-        d_def = cfg['dataset']['define']
+        dexc = None
         log.debug(60 * '-')
         log.info('Defining columns in RDF before evaluating classifier')
         log.debug(60 * '-')
         for name, expr in d_def.items():
+            expr = expr.replace('.', '_')
+
             log.debug(f'{name:<20}{"<---":20}{expr:<100}')
-            rdf = rdf.Define(name, expr)
+            try:
+                rdf = rdf.Define(name, expr)
+            except TypeError as exc:
+                log.error(f'Cannot define {name}={expr}')
+                dexc = exc
+
+        if dexc is not None:
+            raise TypeError('Could not define at least one column') from dexc
 
         return rdf
     # --------------------------------------------
@@ -68,21 +132,25 @@ class CVPredict:
 
         return cfg['dataset']['nan']
     # --------------------------------------------
-    def _replace_nans(self, df : pnd.DataFrame) -> pnd.DataFrame:
+    def _replace_nans(self, df_ft : pnd.DataFrame) -> pnd.DataFrame:
+        '''
+        Funtion replaces nans in user specified columns with user specified values
+        These NaNs are expected
+        '''
         if len(self._d_nan_rep) == 0:
             log.debug('Not doing any NaN replacement')
-            return df
+            return df_ft
 
         log.info(60 * '-')
         log.info('Doing NaN replacements')
         log.info(60 * '-')
         for var, val in self._d_nan_rep.items():
             log.info(f'{var:<20}{"--->":20}{val:<20.3f}')
-            df[var] = df[var].fillna(val)
+            df_ft[var] = df_ft[var].fillna(val)
 
-        return df
+        return df_ft
     # --------------------------------------------
-    def _get_df(self):
+    def _get_df(self) -> pnd.DataFrame:
         '''
         Will make ROOT rdf into dataframe and return it
         '''
@@ -90,11 +158,11 @@ class CVPredict:
         l_ft  = model.features
         d_data= self._rdf.AsNumpy(l_ft)
         df_ft = pnd.DataFrame(d_data)
-        df_ft = self._replace_nans(df_ft)
-        df_ft = ut.patch_and_tag(df_ft)
-
-        if 'patched_indices' in df_ft.attrs:
-            self._arr_patch = df_ft.attrs['patched_indices']
+        df_ft = self._replace_nans(df_ft=df_ft)
+        df_ft = self._tag_skipped(df_ft=df_ft)
+        df_ft = ut.tag_nans(
+            df      = df_ft,
+            indexes = self._index_skip)
 
         nfeat = len(l_ft)
         log.info(f'Found {nfeat} features')
@@ -103,6 +171,24 @@ class CVPredict:
 
         return df_ft
     # --------------------------------------------
+    def _tag_skipped(self, df_ft : pnd.DataFrame) -> pnd.DataFrame:
+        '''
+        Will drop rows with features where column with name _skip_name (currently "_skip_mva_prediction") has values of 1
+        '''
+        if self._skip_index_column not in self._l_column:
+            log.debug(f'Not dropping any rows through: {self._skip_index_column}')
+            return df_ft
+
+        log.info(f'Dropping rows through: {self._skip_index_column}')
+        arr_drop                = self._rdf.AsNumpy([self._skip_index_column])[self._skip_index_column]
+
+        if self._index_skip in df_ft.attrs:
+            raise ValueError(f'Feature dataframe already contains attribute: {self._index_skip}')
+
+        df_ft.attrs[self._index_skip] = numpy.where(arr_drop == 1)[0]
+
+        return df_ft
+    # --------------------------------------------
     def _non_overlapping_hashes(self, model, df_ft):
         '''
         Will return True if hashes of model and data do not overlap
@@ -147,8 +233,8 @@ class CVPredict:
         '''
         Evaluate the dataset for one of the folds, by taking the model and the full dataset
         '''
-        s_dat_hash = set(df_ft.index)
-        s_mod_hash = model.hashes
+        s_dat_hash : set[str] = set(df_ft.index)
+        s_mod_hash : set[str] = model.hashes
 
         s_dif_hash = s_dat_hash - s_mod_hash
 
@@ -164,19 +250,29 @@ class CVPredict:
         d_prob = dict(zip(l_hash, l_prob))
         nfeat  = len(df_ft_group)
         nprob  = len(l_prob)
-        log.debug(f'{nfeat:<10}{"->":10}{nprob:<10}')
+
+        if nfeat != nprob:
+            raise ValueError(f'Number of features and probabilities do not agree: {nfeat} != {nprob}')
 
         return d_prob
     # --------------------------------------------
-    def _patch_probabilities(self, arr_prb : numpy.ndarray) -> numpy.ndarray:
-        if not hasattr(self, '_arr_patch'):
-            return arr_prb
+    def _predict_signal_probabilities(
+            self,
+            model : CVClassifier,
+            df_ft : pnd.DataFrame) -> numpy.ndarray:
+        '''
+        Takes model and features dataframe, returns array of signal probabilities
+        '''
+        if self._non_overlapping_hashes(model, df_ft):
+            log.debug('No intersecting hashes found between model and data')
+            arr_prb = model.predict_proba(df_ft)
+        else:
+            log.info('Intersecting hashes found between model and data')
+            arr_prb = self._predict_with_overlap(df_ft)
 
-        nentries = len(self._arr_patch)
-        log.warning(f'Patching {nentries} probabilities with -1')
-        arr_prb[self._arr_patch] = -1
+        arr_sig_prb = arr_prb.T[1]
 
-        return arr_prb
+        return arr_sig_prb
     # --------------------------------------------
     def predict(self) -> numpy.ndarray:
         '''
@@ -187,15 +283,22 @@ class CVPredict:
         df_ft = self._get_df()
         model = self._l_model[0]
 
-        if self._non_overlapping_hashes(model, df_ft):
-            log.debug('No intersecting hashes found between model and data')
-            arr_prb = model.predict_proba(df_ft)
-        else:
-            log.info('Intersecting hashes found between model and data')
-            arr_prb = self._predict_with_overlap(df_ft)
+        arr_keep = None
+        arr_skip = None
+        if self._index_skip in df_ft.attrs:
+            arr_skip = df_ft.attrs[self._index_skip]
+            df_ft    = df_ft.drop(arr_skip)
+            arr_keep = df_ft.index.to_numpy()
+
+        arr_sig_prb  = self._predict_signal_probabilities(
+                model = model,
+                df_ft = df_ft)
+
+        if arr_skip is None:
+            return arr_sig_prb
 
-        arr_prb = self._patch_probabilities(arr_prb)
-        arr_prb = arr_prb.T[1]
+        arr_all_sig_prb           = numpy.full(self._nrows, self._dummy_score)
+        arr_all_sig_prb[arr_keep] = arr_sig_prb
 
-        return arr_prb
+        return arr_all_sig_prb
 # ---------------------------------------