From 4e6062b23b53582b173572af3d60c8bc3fb34ec7 Mon Sep 17 00:00:00 2001
From: Chandan Singh <chandan_singh@berkeley.edu>
Date: Thu, 18 Jul 2019 06:03:37 -0700
Subject: [PATCH] notes on pip installation

---
 notebooks/1_model_based.ipynb | 12 ++++++------
 readme.md                     | 14 +++++++++-----
 2 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/notebooks/1_model_based.ipynb b/notebooks/1_model_based.ipynb
index 575d9c4e..75b8a922 100644
--- a/notebooks/1_model_based.ipynb
+++ b/notebooks/1_model_based.ipynb
@@ -92,7 +92,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sys.path.append('models/slim')\n",
+    "sys.path.append('../imodels/slim')\n",
     "from SLIM import SLIM"
    ]
   },
@@ -292,8 +292,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sys.path.append('models/bayesian_rule_lists')\n",
-    "sys.path.append('models/bayesian_rule_lists/discretization')\n",
+    "sys.path.append('../imodels/bayesian_rule_lists')\n",
+    "sys.path.append('../imodels/bayesian_rule_lists/discretization')\n",
     "from RuleListClassifier import *\n",
     "from sklearn.datasets import fetch_openml\n",
     "from sklearn.model_selection import train_test_split\n",
@@ -357,8 +357,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sys.path.append('models/optimal_classification_tree/pyoptree')\n",
-    "sys.path.append('models/optimal_classification_tree/')"
+    "sys.path.append('../imodels/optimal_classification_tree/pyoptree')\n",
+    "sys.path.append('../imodels/optimal_classification_tree/')"
    ]
   },
   {
@@ -447,5 +447,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }
diff --git a/readme.md b/readme.md
index bb461d52..f6fcdd5a 100644
--- a/readme.md
+++ b/readme.md
@@ -2,9 +2,8 @@
 
 Code for implementations of interpretable machine learning models and demos of how to use various interpretability techniques (with accompanying slides [here](https://docs.google.com/presentation/d/1RIdbV279r20marRrN0b1bu2z9STkrivsMDa_Dauk8kE/present)).
 
-
 ### Code implementations
-Provides scikit-learn style wrappers/implementations of different interpretable models (see readmes in individual folders within [models](models) for details)
+Provides scikit-learn style wrappers/implementations of different interpretable models (see readmes in individual folders within [imodels](imodels) for details)
 
 - [bayesian rule lists](https://arxiv.org/abs/1602.08610)
 - [optimal classification tree](https://link.springer.com/article/10.1007/s10994-017-5633-9)
@@ -18,12 +17,17 @@ The demos are contained in 3 main [notebooks](notebooks), summarized in [cheat_s
 3. [uncertainty.ipynb](notebooks/uncertainty.ipynb) - code to get uncertainty estimates for a model
 
 ### Installation / quickstart
-To install, `pip install git+https://github.com/csinva/interpretability-implementations-demos`
+The interpretable models within the [imodels](imodels) folder can be easily installed and used.
 
-```
+`pip install git+https://github.com/csinva/interpretability-implementations-demos`
 
 ```
-
+from imodels.bayesian_rule_lists import RuleListClassifier
+model = RuleListClassifier()
+model.fit(X_train, y_train)
+model.score(X_test, y_test)
+preds = model.predict(X_test)
+```
 
 ### References / further reading