From 16caf521898a5f38b260dc2e0efe6797de441fb6 Mon Sep 17 00:00:00 2001
From: wfondrie <wfondrie@umaryland.edu>
Date: Mon, 13 Jul 2020 16:29:47 -0700
Subject: [PATCH] Added __repr__ to major classes

---
 mokapot/confidence.py |  9 +++++++++
 mokapot/dataset.py    | 21 ++++++++++++++++++---
 mokapot/model.py      |  9 ++++++++-
 3 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/mokapot/confidence.py b/mokapot/confidence.py
index a77ebd68..4709ff20 100644
--- a/mokapot/confidence.py
+++ b/mokapot/confidence.py
@@ -190,6 +190,15 @@ def __init__(self, psms, scores, desc=True, eval_fdr=0.01):
 
         self._assign_confidence(desc=desc)
 
+    def __repr__(self):
+        """How to print the class"""
+        pass_psms = (self.psms["mokapot q-value"] <= self._eval_fdr).sum()
+        pass_peps = (self.peptides["mokapot q-value"] <= self._eval_fdr).sum()
+
+        return ("A mokapot.confidence.LinearConfidence object:\n"
+                f"\t- PSMs at q<={self._eval_fdr:g}: {pass_psms}\n"
+                f"\t- Peptides at q<={self._eval_fdr:g}: {pass_peps}")
+
     def _assign_confidence(self, desc=True):
         """
         Assign confidence to PSMs and peptides.
diff --git a/mokapot/dataset.py b/mokapot/dataset.py
index 0f6e1d7e..01bcc0f7 100644
--- a/mokapot/dataset.py
+++ b/mokapot/dataset.py
@@ -309,9 +309,9 @@ class LinearPsmDataset(PsmDataset):
     metadata : pandas.DataFrame
     features : pandas.DataFrame
     spectra : pandas.DataFrame
+    peptides: pandas.DataFrame
     targets : numpy.ndarray
     columns : list of str
-
     """
     def __init__(self,
                  psms,
@@ -349,16 +349,31 @@ def __init__(self,
 
         if not num_targets:
             raise ValueError("No target PSMs were detected.")
-        elif not num_decoys:
+        if not num_decoys:
             raise ValueError("No decoy PSMs were detected.")
-        elif not len(self.data):
+        if not self.data.shape[0]:
             raise ValueError("No PSMs were detected.")
 
+    def __repr__(self):
+        """How to print the class"""
+        return (f"A mokapot.dataset.LinearPsmDataset with {len(self.data)} "
+                "PSMs:\n"
+                f"\t- target PSMs: {self.targets.sum()}\n"
+                f"\t- decoy PSMs: {self.targets.sum()}\n"
+                f"\t- unique spectra: {len(self.spectra.drop_duplicates())}\n"
+                f"\t- unique peptides: {len(self.peptides.drop_duplicates())}\n"
+                f"\t- features: {self._feature_columns}")
+
     @property
     def targets(self):
         """An array indicating whether each PSM is a target sequence."""
         return self.data[self._target_column].values
 
+    @property
+    def peptides(self):
+        """A :py:class:`pandas.DataFrame` of peptide columns."""
+        return self.data.loc[:, self._peptide_columns]
+
     def _update_labels(self, scores, fdr_threshold=0.01, desc=True):
         """
         Return the label for each PSM, given it's score.
diff --git a/mokapot/model.py b/mokapot/model.py
index e2182035..e220d74b 100644
--- a/mokapot/model.py
+++ b/mokapot/model.py
@@ -84,7 +84,6 @@ def __init__(self, estimator=None, scaler=None, is_trained=False):
         self.estimator = base.clone(estimator)
         self.features = None
         self.is_trained = is_trained
-        self._base_params = self.estimator.get_params()
 
         if scaler == "as-is":
             self.scaler = DummyScaler()
@@ -93,6 +92,14 @@ def __init__(self, estimator=None, scaler=None, is_trained=False):
         else:
             self.scaler = base.clone(scaler)
 
+    def __repr__(self):
+        """How to print the class"""
+        trained = {True: "A trained", False: "An untrained"}
+
+        return (f"{trained[self.is_trained]} mokapot.model.Model object:\n"
+                f"\testimator: {self.estimator}\n"
+                f"\tscaler: {self.scaler}\n"
+                f"\tfeatures: {self.features}")
 
     def save(self, out_file):
         """