From 5ea59241c73781634e46db85145099a7755a97b0 Mon Sep 17 00:00:00 2001
From: amarv <amarvenu@stanford.edu>
Date: Wed, 17 Jan 2024 17:55:41 -0800
Subject: [PATCH 01/13] add support for multiplier bootstrap uniform confidence
 band error bars for uplift curves

Signed-off-by: amarv <amarvenu@stanford.edu>
---
 econml/tests/test_drtester.py   |  10 +-
 econml/validate/drtester.py     |   4 +-
 econml/validate/results.py      |  60 ++++++--
 econml/validate/utils.py        |  25 +++-
 notebooks/CATE validation.ipynb | 235 ++++++++++++++++++++++++--------
 5 files changed, 259 insertions(+), 75 deletions(-)

diff --git a/econml/tests/test_drtester.py b/econml/tests/test_drtester.py
index 6b08882be..ec8e6af2e 100644
--- a/econml/tests/test_drtester.py
+++ b/econml/tests/test_drtester.py
@@ -148,8 +148,8 @@ def test_binary(self):
                 self.assertRaises(ValueError, res.plot_toc, k)
             else:  # real treatment, k = 1
                 self.assertTrue(res.plot_cal(k) is not None)
-                self.assertTrue(res.plot_qini(k) is not None)
-                self.assertTrue(res.plot_toc(k) is not None)
+                self.assertTrue(res.plot_qini(k, 'ucb2') is not None)
+                self.assertTrue(res.plot_toc(k, 'ucb1') is not None)
 
         self.assertLess(res_df.blp_pval.values[0], 0.05)  # heterogeneity
         self.assertGreater(res_df.cal_r_squared.values[0], 0)  # good R2
@@ -278,5 +278,11 @@ def test_exceptions(self):
         qini_res = my_dr_tester.evaluate_uplift(Xval, Xtrain)
         self.assertLess(qini_res.pvals[0], 0.05)
 
+        with self.assertRaises(Exception) as exc:
+            qini_res.plot_uplift(metric='blah')
+        self.assertTrue(
+            str(exc.exception) == "Invalid error type; must be one of [None, 'ucb2', 'ucb1']"
+        )
+
         autoc_res = my_dr_tester.evaluate_uplift(Xval, Xtrain, metric='toc')
         self.assertLess(autoc_res.pvals[0], 0.05)
diff --git a/econml/validate/drtester.py b/econml/validate/drtester.py
index bcf4c0141..260967808 100644
--- a/econml/validate/drtester.py
+++ b/econml/validate/drtester.py
@@ -492,9 +492,9 @@ def evaluate_uplift(
         metric: str = 'qini'
     ) -> UpliftEvaluationResults:
         """
-        Calculates QINI coefficient for the given model as in Radcliffe (2007), where units are ordered by predicted
+        Calculates uplift curves and coefficients for the given model, where units are ordered by predicted
         CATE values and a running measure of the average treatment effect in each cohort is kept as we progress
-        through ranks. The QINI coefficient is then the area under the resulting curve, with a value of 0 interpreted
+        through ranks. The uplift coefficient is then the area under the resulting curve, with a value of 0 interpreted
         as corresponding to a model with randomly assigned CATE coefficients. All calculations are performed on
         validation dataset results, using the training set as input.
 
diff --git a/econml/validate/results.py b/econml/validate/results.py
index d236757a7..03a19fc98 100644
--- a/econml/validate/results.py
+++ b/econml/validate/results.py
@@ -188,7 +188,7 @@ def summary(self):
         }).round(3)
         return res
 
-    def plot_uplift(self, tmt: Any):
+    def plot_uplift(self, tmt: Any, err_type: str = None):
         """
         Plots uplift curves.
 
@@ -197,6 +197,10 @@ def plot_uplift(self, tmt: Any):
         tmt: any (sortable)
             Name of treatment to plot.
 
+        err_type: str
+            Type of error to plot. Accepted values are normal (None), two-sided uniform confidence band ('ucb2'),
+            or 1-sided uniform confidence band).
+
         Returns
         -------
         matplotlib plot with percentage treated on x-axis and uplift metric (and 95% CI) on y-axis
@@ -205,18 +209,38 @@ def plot_uplift(self, tmt: Any):
             raise ValueError(f'Invalid treatment; must be one of {self.treatments[1:]}')
 
         df = self.curves[tmt].copy()
-        df['95_err'] = 1.96 * df['err']
+
+        if err_type is None:
+            df['95_err'] = 1.96 * df['err']
+        elif err_type == 'ucb2':
+            df['95_err'] = df['uniform_critical_value'] * df['err']
+        elif err_type == 'ucb1':
+            df['95_err'] = df['uniform_one_side_critical_value'] * df['err']
+        else:
+            raise ValueError("Invalid error type; must be one of [None, 'ucb2', 'ucb1']")
+
         res = self.summary()
         coeff = round(res.loc[res['treatment'] == tmt]['est'].values[0], 3)
         err = round(res.loc[res['treatment'] == tmt]['se'].values[0], 3)
-        fig = df.plot(
-            kind='scatter',
-            x='Percentage treated',
-            y='value',
-            yerr='95_err',
-            ylabel='Gain over Random',
-            title=f"Treatment = {tmt}, Integral = {coeff} +/- {err}"
-        )
+
+        if err_type == 'ucb1':
+            fig = df.plot(
+                kind='scatter',
+                x='Percentage treated',
+                y='value',
+                yerr=[[df['95_err'], np.zeros(len(df))]],
+                ylabel='Gain over Random',
+                title=f"Treatment = {tmt}, Integral = {coeff} +/- {err}"
+            )
+        else:
+            fig = df.plot(
+                kind='scatter',
+                x='Percentage treated',
+                y='value',
+                yerr='95_err',
+                ylabel='Gain over Random',
+                title=f"Treatment = {tmt}, Integral = {coeff} +/- {err}"
+            )
 
         return fig
 
@@ -290,7 +314,7 @@ def plot_cal(self, tmt: int):
         """
         return self.cal.plot_cal(tmt)
 
-    def plot_qini(self, tmt: int):
+    def plot_qini(self, tmt: int, err_type: str = None):
         """
         Plots QINI curves.
 
@@ -299,13 +323,17 @@ def plot_qini(self, tmt: int):
         tmt: integer
             Treatment level to plot
 
+        err_type: str
+            Type of error to plot. Accepted values are normal (None), two-sided uniform confidence band ('ucb2'),
+            or 1-sided uniform confidence band).
+
         Returns
         -------
         matplotlib plot with percentage treated on x-axis and QINI value (and 95% CI) on y-axis
         """
-        return self.qini.plot_uplift(tmt)
+        return self.qini.plot_uplift(tmt, err_type)
 
-    def plot_toc(self, tmt: int):
+    def plot_toc(self, tmt: int, err_type: str = None):
         """
         Plots TOC curves.
 
@@ -314,8 +342,12 @@ def plot_toc(self, tmt: int):
         tmt: integer
             Treatment level to plot
 
+        err_type: str
+            Type of error to plot. Accepted values are normal (None), two-sided uniform confidence band ('ucb2'),
+            or 1-sided uniform confidence band).
+
         Returns
         -------
         matplotlib plot with percentage treated on x-axis and TOC value (and 95% CI) on y-axis
         """
-        return self.toc.plot_uplift(tmt)
+        return self.toc.plot_uplift(tmt, err_type)
diff --git a/econml/validate/utils.py b/econml/validate/utils.py
index 50dc3235d..79e5a6f57 100644
--- a/econml/validate/utils.py
+++ b/econml/validate/utils.py
@@ -56,8 +56,10 @@ def calc_uplift(
     metric: str
 ) -> Tuple[float, float, pd.DataFrame]:
     """
-    Helper function for QINI curve generation and QINI coefficient calculation.
-    See documentation for "evaluate_qini" method for more details.
+    Helper function for uplift curve generation and coefficient calculation.
+    Calculates uplift curve points, integral, and errors on both points and integral.
+    Also calculates appropriate critical value multipliers for confidence interval construction (via multiplier bootstrap).
+    See documentation for "drtester.evaluate_uplift" method for more details.
 
     Parameters
     ----------
@@ -98,6 +100,21 @@ def calc_uplift(
 
         toc_std[it] = np.sqrt(np.mean(toc_psi[it] ** 2) / n)  # standard error of tau(q)
 
+    if dr_val.shape[0] > 1e6:  # avoid computational issues if dataset too large
+        mboot = np.zeros((len(qs), 1000))
+        for it in range(1000):
+            w = np.random.normal(0, 1, size=(n,))
+            mboot[:, it] = (toc_psi / toc_std.reshape(-1, 1)) @ w / n
+    else:
+        w = np.random.normal(0, 1, size=(n, 1000))
+        mboot = (toc_psi / toc_std.reshape(-1, 1)) @ w / n
+
+    max_mboot = np.max(np.abs(mboot), axis=0)
+    uniform_critical_value = np.percentile(max_mboot, 95)
+
+    min_mboot = np.min(mboot, axis=0)
+    uniform_one_side_critical_value = np.abs(np.percentile(min_mboot, 5))
+
     coeff_psi = np.sum(toc_psi[:-1] * np.diff(percentiles).reshape(-1, 1) / 100, 0)
     coeff = np.sum(toc[:-1] * np.diff(percentiles) / 100)
     coeff_stderr = np.sqrt(np.mean(coeff_psi ** 2) / n)
@@ -105,7 +122,9 @@ def calc_uplift(
     curve_df = pd.DataFrame({
         'Percentage treated': 100 - percentiles,
         'value': toc,
-        'err': toc_std
+        'err': toc_std,
+        'uniform_critical_value': uniform_critical_value,
+        'uniform_one_side_critical_value': uniform_one_side_critical_value
     })
 
     return coeff, coeff_stderr, curve_df
diff --git a/notebooks/CATE validation.ipynb b/notebooks/CATE validation.ipynb
index 4f816bfac..6a5394b4d 100644
--- a/notebooks/CATE validation.ipynb	
+++ b/notebooks/CATE validation.ipynb	
@@ -133,7 +133,7 @@
     {
      "data": {
       "text/plain": [
-       "<econml.dml.dml.DML at 0x7fecb05fecd0>"
+       "<econml.dml.dml.DML at 0x7f7d1bcdb700>"
       ]
      },
      "execution_count": 4,
@@ -199,30 +199,30 @@
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>1</td>\n",
-       "      <td>-0.137</td>\n",
-       "      <td>0.142</td>\n",
-       "      <td>0.335</td>\n",
-       "      <td>-0.015</td>\n",
-       "      <td>0.021</td>\n",
-       "      <td>0.242</td>\n",
-       "      <td>-0.032</td>\n",
-       "      <td>0.063</td>\n",
-       "      <td>0.306</td>\n",
-       "      <td>-5.506</td>\n",
+       "      <td>0.044</td>\n",
+       "      <td>0.238</td>\n",
+       "      <td>0.854</td>\n",
+       "      <td>-0.009</td>\n",
+       "      <td>0.023</td>\n",
+       "      <td>0.352</td>\n",
+       "      <td>-0.011</td>\n",
+       "      <td>0.054</td>\n",
+       "      <td>0.42</td>\n",
+       "      <td>-9.922</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>2</td>\n",
-       "      <td>1.003</td>\n",
+       "      <td>1.032</td>\n",
        "      <td>0.062</td>\n",
        "      <td>0.000</td>\n",
-       "      <td>0.375</td>\n",
+       "      <td>0.373</td>\n",
        "      <td>0.024</td>\n",
        "      <td>0.000</td>\n",
-       "      <td>1.026</td>\n",
-       "      <td>0.060</td>\n",
-       "      <td>0.000</td>\n",
-       "      <td>0.090</td>\n",
+       "      <td>1.049</td>\n",
+       "      <td>0.058</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>-0.090</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -230,12 +230,12 @@
       ],
       "text/plain": [
        "   treatment  blp_est  blp_se  blp_pval  qini_est  qini_se  qini_pval  \\\n",
-       "0          1    0.078   0.220     0.722    -0.011    0.023      0.322   \n",
-       "1          2    1.003   0.062     0.000     0.375    0.024      0.000   \n",
+       "0          1    0.044   0.238     0.854    -0.009    0.023      0.352   \n",
+       "1          2    1.032   0.062     0.000     0.373    0.024      0.000   \n",
        "\n",
        "   autoc_est  autoc_se  autoc_pval  cal_r_squared  \n",
-       "0     -0.032     0.063       0.306         -5.506  \n",
-       "1      1.026     0.060       0.000          0.090  "
+       "0     -0.011     0.054        0.42         -9.922  \n",
+       "1      1.049     0.058        0.00         -0.090  "
       ]
      },
      "execution_count": 5,
@@ -263,7 +263,7 @@
     {
      "data": {
       "text/plain": [
-       "<Axes: title={'center': 'Treatment = 1, Calibration R^2 = -9.163'}, xlabel='Group Mean CATE', ylabel='GATE'>"
+       "<Axes: title={'center': 'Treatment = 1, Calibration R^2 = -9.922'}, xlabel='Group Mean CATE', ylabel='GATE'>"
       ]
      },
      "execution_count": 6,
@@ -272,7 +272,7 @@
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -293,7 +293,7 @@
     {
      "data": {
       "text/plain": [
-       "<Axes: title={'center': 'Treatment = 2, Calibration R^2 = -0.178'}, xlabel='Group Mean CATE', ylabel='GATE'>"
+       "<Axes: title={'center': 'Treatment = 2, Calibration R^2 = -0.09'}, xlabel='Group Mean CATE', ylabel='GATE'>"
       ]
      },
      "execution_count": 7,
@@ -302,7 +302,7 @@
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -323,7 +323,7 @@
     {
      "data": {
       "text/plain": [
-       "<Axes: title={'center': 'Treatment = 1, Integral = -0.015 +/- 0.021'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
+       "<Axes: title={'center': 'Treatment = 1, Integral = -0.009 +/- 0.023'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
       ]
      },
      "execution_count": 8,
@@ -332,7 +332,7 @@
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -362,7 +362,7 @@
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -383,7 +383,7 @@
     {
      "data": {
       "text/plain": [
-       "<Axes: title={'center': 'Treatment = 1, Integral = -0.032 +/- 0.063'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
+       "<Axes: title={'center': 'Treatment = 1, Integral = -0.011 +/- 0.054'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
       ]
      },
      "execution_count": 10,
@@ -392,7 +392,7 @@
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -413,7 +413,7 @@
     {
      "data": {
       "text/plain": [
-       "<Axes: title={'center': 'Treatment = 2, Integral = 1.026 +/- 0.06'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
+       "<Axes: title={'center': 'Treatment = 2, Integral = 1.049 +/- 0.058'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
       ]
      },
      "execution_count": 11,
@@ -422,7 +422,7 @@
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -439,12 +439,79 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### T-Learner"
+    "We can also plot error bars with uniform confidence bands (UCB), either two-sided (ucb2) or 1-sided (ucb1)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: title={'center': 'Treatment = 2, Integral = 0.373 +/- 0.024'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "res_dml.plot_qini(tmt=2, err_type='ucb2')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: title={'center': 'Treatment = 2, Integral = 1.049 +/- 0.058'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "res_dml.plot_toc(tmt=2, err_type='ucb1')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### T-Learner"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
    "metadata": {
     "collapsed": false,
     "jupyter": {
@@ -493,9 +560,9 @@
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>1</td>\n",
-       "      <td>-0.184</td>\n",
+       "      <td>-0.185</td>\n",
        "      <td>0.111</td>\n",
-       "      <td>0.098</td>\n",
+       "      <td>0.096</td>\n",
        "      <td>-0.044</td>\n",
        "      <td>0.022</td>\n",
        "      <td>0.023</td>\n",
@@ -507,7 +574,7 @@
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>2</td>\n",
-       "      <td>0.717</td>\n",
+       "      <td>0.716</td>\n",
        "      <td>0.060</td>\n",
        "      <td>0.000</td>\n",
        "      <td>0.371</td>\n",
@@ -524,15 +591,15 @@
       ],
       "text/plain": [
        "   treatment  blp_est  blp_se  blp_pval  qini_est  qini_se  qini_pval  \\\n",
-       "0          1   -0.184   0.111     0.098    -0.044    0.022      0.022   \n",
-       "1          2    0.717   0.060     0.000     0.371    0.025      0.000   \n",
+       "0          1   -0.185   0.111     0.096    -0.044    0.022      0.023   \n",
+       "1          2    0.716   0.060     0.000     0.371    0.025      0.000   \n",
        "\n",
        "   autoc_est  autoc_se  autoc_pval  cal_r_squared  \n",
        "0     -0.083     0.057       0.071         -2.747  \n",
        "1      1.028     0.059       0.000          0.626  "
       ]
      },
-     "execution_count": 12,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -551,16 +618,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<Axes: title={'center': 'Treatment = 1, Calibration R^2 = -2.623'}, xlabel='Group Mean CATE', ylabel='GATE'>"
+       "<Axes: title={'center': 'Treatment = 1, Calibration R^2 = -2.747'}, xlabel='Group Mean CATE', ylabel='GATE'>"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -581,16 +648,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<Axes: title={'center': 'Treatment = 2, Calibration R^2 = 0.627'}, xlabel='Group Mean CATE', ylabel='GATE'>"
+       "<Axes: title={'center': 'Treatment = 2, Calibration R^2 = 0.626'}, xlabel='Group Mean CATE', ylabel='GATE'>"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -611,7 +678,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -620,7 +687,7 @@
        "<Axes: title={'center': 'Treatment = 1, Integral = -0.044 +/- 0.022'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -641,7 +708,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -650,7 +717,7 @@
        "<Axes: title={'center': 'Treatment = 2, Integral = 0.371 +/- 0.025'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -671,7 +738,37 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: title={'center': 'Treatment = 2, Integral = 0.373 +/- 0.024'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "res_dml.plot_qini(tmt=2, err_type='ucb1')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
@@ -680,7 +777,7 @@
        "<Axes: title={'center': 'Treatment = 1, Integral = -0.083 +/- 0.057'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -701,7 +798,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -710,7 +807,7 @@
        "<Axes: title={'center': 'Treatment = 2, Integral = 1.028 +/- 0.059'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -729,6 +826,36 @@
     "res_t.plot_toc(2)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: title={'center': 'Treatment = 2, Integral = 1.049 +/- 0.058'}, xlabel='Percentage treated', ylabel='Gain over Random'>"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "res_dml.plot_toc(tmt=2, err_type='ucb2')"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -739,7 +866,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "dev_env",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },

From 0cfef58b4807b26cfbebeb48f467248e3cc6327b Mon Sep 17 00:00:00 2001
From: amarv <amarvenu@stanford.edu>
Date: Wed, 17 Jan 2024 18:36:49 -0800
Subject: [PATCH 02/13] update test cases + validate example notebook

Signed-off-by: amarv <amarvenu@stanford.edu>
---
 econml/tests/test_drtester.py   |  4 ++--
 econml/validate/utils.py        | 13 ++++---------
 notebooks/CATE validation.ipynb |  2 +-
 3 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/econml/tests/test_drtester.py b/econml/tests/test_drtester.py
index ec8e6af2e..8d4d0ced9 100644
--- a/econml/tests/test_drtester.py
+++ b/econml/tests/test_drtester.py
@@ -5,7 +5,7 @@
 import scipy.stats as st
 from sklearn.ensemble import RandomForestClassifier, GradientBoostingRegressor
 
-from econml.validate.drtester import DRtester
+from validate.drtester import DRtester
 from econml.dml import DML
 
 
@@ -279,7 +279,7 @@ def test_exceptions(self):
         self.assertLess(qini_res.pvals[0], 0.05)
 
         with self.assertRaises(Exception) as exc:
-            qini_res.plot_uplift(metric='blah')
+            qini_res.plot_uplift(tmt=1, err_type='blah')
         self.assertTrue(
             str(exc.exception) == "Invalid error type; must be one of [None, 'ucb2', 'ucb1']"
         )
diff --git a/econml/validate/utils.py b/econml/validate/utils.py
index 79e5a6f57..7fcfd21ed 100644
--- a/econml/validate/utils.py
+++ b/econml/validate/utils.py
@@ -53,7 +53,8 @@ def calc_uplift(
     cate_preds_val: np.array,
     dr_val: np.array,
     percentiles: np.array,
-    metric: str
+    metric: str,
+
 ) -> Tuple[float, float, pd.DataFrame]:
     """
     Helper function for uplift curve generation and coefficient calculation.
@@ -100,14 +101,8 @@ def calc_uplift(
 
         toc_std[it] = np.sqrt(np.mean(toc_psi[it] ** 2) / n)  # standard error of tau(q)
 
-    if dr_val.shape[0] > 1e6:  # avoid computational issues if dataset too large
-        mboot = np.zeros((len(qs), 1000))
-        for it in range(1000):
-            w = np.random.normal(0, 1, size=(n,))
-            mboot[:, it] = (toc_psi / toc_std.reshape(-1, 1)) @ w / n
-    else:
-        w = np.random.normal(0, 1, size=(n, 1000))
-        mboot = (toc_psi / toc_std.reshape(-1, 1)) @ w / n
+    w = np.random.normal(0, 1, size=(n, 1000))
+    mboot = (toc_psi / toc_std.reshape(-1, 1)) @ w / n
 
     max_mboot = np.max(np.abs(mboot), axis=0)
     uniform_critical_value = np.percentile(max_mboot, 95)
diff --git a/notebooks/CATE validation.ipynb b/notebooks/CATE validation.ipynb
index 6a5394b4d..c0b3c23a8 100644
--- a/notebooks/CATE validation.ipynb	
+++ b/notebooks/CATE validation.ipynb	
@@ -133,7 +133,7 @@
     {
      "data": {
       "text/plain": [
-       "<econml.dml.dml.DML at 0x7f7d1bcdb700>"
+       "<econml.dml.dml.DML at 0x7f7b4836cd00>"
       ]
      },
      "execution_count": 4,

From 7cd8b1cc8756964e97e24a2e38f39d3dce6d7f30 Mon Sep 17 00:00:00 2001
From: amarv <amarvenu@stanford.edu>
Date: Mon, 22 Jan 2024 10:32:21 -0800
Subject: [PATCH 03/13] fix test import statement

Signed-off-by: amarv <amarvenu@stanford.edu>
---
 econml/tests/test_drtester.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/econml/tests/test_drtester.py b/econml/tests/test_drtester.py
index 8d4d0ced9..ec40ab17e 100644
--- a/econml/tests/test_drtester.py
+++ b/econml/tests/test_drtester.py
@@ -5,7 +5,7 @@
 import scipy.stats as st
 from sklearn.ensemble import RandomForestClassifier, GradientBoostingRegressor
 
-from validate.drtester import DRtester
+from econml.validate.drtester import DRtester
 from econml.dml import DML
 
 

From 6ab771150a7ca5dd6e3024e2551db325b2342b4a Mon Sep 17 00:00:00 2001
From: amarv <amarvenu@stanford.edu>
Date: Wed, 24 Jan 2024 11:34:43 -0800
Subject: [PATCH 04/13] add number of bootstrap samples as settable parameter
 for uplift modeling

Signed-off-by: amarv <amarvenu@stanford.edu>
---
 econml/validate/drtester.py | 24 ++++++++++++++++--------
 econml/validate/utils.py    |  8 +++++---
 2 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/econml/validate/drtester.py b/econml/validate/drtester.py
index 260967808..4442510dc 100644
--- a/econml/validate/drtester.py
+++ b/econml/validate/drtester.py
@@ -86,7 +86,6 @@ class DRtester:
     References
     ----------
 
-
     [Chernozhukov2022] V. Chernozhukov et al.
     Generic Machine Learning Inference on Heterogeneous Treatment Effects in Randomized Experiments
     arXiv preprint arXiv:1712.04802, 2022.
@@ -97,7 +96,6 @@ class DRtester:
     arXiv preprint 	arXiv:2008.10109, 2020.
     `<https://arxiv.org/abs/2008.10109>`_
 
-
     [Radcliffe2007] N. Radcliffe
     Using control groups to target on predicted lift: Building and assessing uplift model.
     Direct Marketing Analytics Journal (2007), pages 14–21.
@@ -489,7 +487,8 @@ def evaluate_uplift(
         Xval: np.array = None,
         Xtrain: np.array = None,
         percentiles: np.array = np.linspace(5, 95, 50),
-        metric: str = 'qini'
+        metric: str = 'qini',
+        n_bootstrap: int = 1000
     ) -> UpliftEvaluationResults:
         """
         Calculates uplift curves and coefficients for the given model, where units are ordered by predicted
@@ -512,6 +511,8 @@ def evaluate_uplift(
             5%.
         metric: string, default 'qini'
             Which type of uplift curve to evaluate. Must be one of ['toc', 'qini']
+        n_bootstrap: integer, default 1000
+            Number of bootstrap samples to run when calculating uniform confidence bands.
 
         Returns
         -------
@@ -532,7 +533,8 @@ def evaluate_uplift(
                 self.cate_preds_val_,
                 self.dr_val_,
                 percentiles,
-                metric
+                metric,
+                n_bootstrap
             )
             coeffs = [coeff]
             errs = [err]
@@ -546,7 +548,8 @@ def evaluate_uplift(
                     self.cate_preds_val_[:, k],
                     self.dr_val_[:, k],
                     percentiles,
-                    metric
+                    metric,
+                    n_bootstrap
                 )
                 coeffs.append(coeff)
                 errs.append(err)
@@ -568,7 +571,8 @@ def evaluate_all(
         self,
         Xval: np.array = None,
         Xtrain: np.array = None,
-        n_groups: int = 4
+        n_groups: int = 4,
+        n_bootstrap: int = 1000
     ) -> EvaluationResults:
         """
         Implements the best linear prediction (`evaluate_blp'), calibration (`evaluate_cal'), uplift curve
@@ -582,6 +586,10 @@ def evaluate_all(
         Xtrain: (n_train x k) matrix, default ``None''
             Training sample features for CATE model. If not specified, then `fit_cate' method must already have been
             implemented
+        n_groups: integer, default 4
+            Number of quantile-based groups used to calculate calibration score.
+        n_bootstrap: integer, default 1000
+            Number of bootstrap samples to run when calculating uniform confidence bands for uplift curves.
 
         Returns
         -------
@@ -595,8 +603,8 @@ def evaluate_all(
 
         blp_res = self.evaluate_blp()
         cal_res = self.evaluate_cal(n_groups=n_groups)
-        qini_res = self.evaluate_uplift(metric='qini')
-        toc_res = self.evaluate_uplift(metric='toc')
+        qini_res = self.evaluate_uplift(metric='qini', n_bootstrap=n_bootstrap)
+        toc_res = self.evaluate_uplift(metric='toc', n_bootstrap=n_bootstrap)
 
         self.res = EvaluationResults(
             blp_res=blp_res,
diff --git a/econml/validate/utils.py b/econml/validate/utils.py
index 7fcfd21ed..159c18a1d 100644
--- a/econml/validate/utils.py
+++ b/econml/validate/utils.py
@@ -54,12 +54,12 @@ def calc_uplift(
     dr_val: np.array,
     percentiles: np.array,
     metric: str,
-
+    n_bootstrap: int = 1000
 ) -> Tuple[float, float, pd.DataFrame]:
     """
     Helper function for uplift curve generation and coefficient calculation.
     Calculates uplift curve points, integral, and errors on both points and integral.
-    Also calculates appropriate critical value multipliers for confidence interval construction (via multiplier bootstrap).
+    Also calculates appropriate critical value multipliers for confidence intervals (via multiplier bootstrap).
     See documentation for "drtester.evaluate_uplift" method for more details.
 
     Parameters
@@ -75,6 +75,8 @@ def calc_uplift(
         Array of percentiles over which the QINI curve should be constructed. Defaults to 5%-95% in intervals of 5%.
     metric: string
         String indicating whether to calculate TOC or QINI; should be one of ['toc', 'qini']
+    n_bootstrap: integer, default 1000
+        Number of bootstrap samples to run when calculating uniform confidence bands.
 
     Returns
     -------
@@ -101,7 +103,7 @@ def calc_uplift(
 
         toc_std[it] = np.sqrt(np.mean(toc_psi[it] ** 2) / n)  # standard error of tau(q)
 
-    w = np.random.normal(0, 1, size=(n, 1000))
+    w = np.random.normal(0, 1, size=(n, n_bootstrap))
     mboot = (toc_psi / toc_std.reshape(-1, 1)) @ w / n
 
     max_mboot = np.max(np.abs(mboot), axis=0)

From 208af1c824d38f7e8a00963c2c46396fda767d91 Mon Sep 17 00:00:00 2001
From: amarv <amarvenu@stanford.edu>
Date: Wed, 24 Jan 2024 12:01:55 -0800
Subject: [PATCH 05/13] update docstrings

Signed-off-by: amarv <amarvenu@stanford.edu>
---
 econml/validate/drtester.py | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/econml/validate/drtester.py b/econml/validate/drtester.py
index 4442510dc..5dd7d2f51 100644
--- a/econml/validate/drtester.py
+++ b/econml/validate/drtester.py
@@ -46,27 +46,39 @@ class DRtester:
     The calibration r-squared metric is similar to the standard R-square score in that it can take any value
     less than or equal to 1, with scores closer to 1 indicating a better calibrated CATE model.
 
-    **QINI**
+    **Uplift Modeling**
 
     Units are ordered by predicted CATE values and a running measure of the average treatment effect in each cohort is
-    kept as we progress through ranks. The QINI coefficient is then the area under the resulting curve, with a value
-    of 0 interpreted as corresponding to a model with randomly assigned CATE coefficients. All calculations are
-    performed on validation dataset results, using the training set as input.
+    kept as we progress through ranks. The resulting TOC curve can then be plotted and its integral calculated and used
+    as a measure of true heterogeneity captured by the CATE model; this integral is referred to as the AUTOC (area
+    under TOC). The QINI curve is a variant of this curve that also incorporates treatment probability; its integral is
+    referred to as the QINI coefficient.
 
-    More formally, the QINI curve is given by the following function:
+    More formally, the TOC and QINI curves are given by the following functions:
 
     .. math::
 
+        \\tau_{TOC}(q) = \\mathrm{Cov}(
+            Y^{DR}(g,p),
+            \\frac{
+                \\mathbb{1}\\{\\hat{\\tau}(Z) \\geq \\hat{\\mu}(q)\\}
+            }{
+                \\mathrm{Pr}(\\hat{\\tau}(Z) \\geq \\hat{\\mu}(q))
+            }
+        )
+
         \\tau_{QINI}(q) = \\mathrm{Cov}(Y^{DR}(g,p), \\mathbb{1}\\{\\hat{\\tau}(Z) \\geq \\hat{\\mu}(q)\\})
 
     Where :math:`q` is the desired quantile, :math:`\\hat{\\mu}` is the quantile function, and :math:`\\hat{\\tau}` is
     the predicted CATE function.
     :math:`Y^{DR}(g,p)` refers to the doubly robust outcome difference (relative to control) for the given observation.
 
-    The QINI coefficient is then given by:
+    The AUTOC and QINI coefficient are then given by:
 
     .. math::
 
+        AUTOC = \\int_0^1 \\tau_{TOC}(q) dq
+
         QINI = \\int_0^1 \\tau_{QINI}(q) dq
 
     Parameters
@@ -80,8 +92,12 @@ class DRtester:
         method and either `predict' (in the case of binary treatment) or `predict_proba' methods (in the case of
         multiple categorical treatments).
 
-    n_splits: integer, default 5
-        Number of splits used to generate cross-validated predictions
+    cate: estimator
+        Fitted conditional average treatment effect (CATE) estimator to be validated.
+
+    cv: int or list, default 5
+        Splitter used for cross-validation. Can be either an integer (corresponding to the number of desired folds)
+        or a list of indices corresponding to membership in each fold.
 
     References
     ----------

From 138cec26732425b57f5e5b1c2d4df387bef05372 Mon Sep 17 00:00:00 2001
From: Amar Venugopal <89877778+amarvenu@users.noreply.github.com>
Date: Wed, 24 Jan 2024 11:17:45 -0800
Subject: [PATCH 06/13] Update econml/validate/results.py

Co-authored-by: Keith Battocchi <kbattocchi@gmail.com>
Signed-off-by: Amar Venugopal <89877778+amarvenu@users.noreply.github.com>
---
 econml/validate/results.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/econml/validate/results.py b/econml/validate/results.py
index 03a19fc98..5f6b3f605 100644
--- a/econml/validate/results.py
+++ b/econml/validate/results.py
@@ -199,7 +199,7 @@ def plot_uplift(self, tmt: Any, err_type: str = None):
 
         err_type: str
             Type of error to plot. Accepted values are normal (None), two-sided uniform confidence band ('ucb2'),
-            or 1-sided uniform confidence band).
+            or 1-sided uniform confidence band ('ucb1').
 
         Returns
         -------

From d86cebe4f41130397637f284da68e0963933edd5 Mon Sep 17 00:00:00 2001
From: Amar Venugopal <89877778+amarvenu@users.noreply.github.com>
Date: Wed, 24 Jan 2024 11:17:54 -0800
Subject: [PATCH 07/13] Update econml/validate/results.py

Co-authored-by: Keith Battocchi <kbattocchi@gmail.com>
Signed-off-by: Amar Venugopal <89877778+amarvenu@users.noreply.github.com>
---
 econml/validate/results.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/econml/validate/results.py b/econml/validate/results.py
index 5f6b3f605..a76e705fb 100644
--- a/econml/validate/results.py
+++ b/econml/validate/results.py
@@ -217,7 +217,7 @@ def plot_uplift(self, tmt: Any, err_type: str = None):
         elif err_type == 'ucb1':
             df['95_err'] = df['uniform_one_side_critical_value'] * df['err']
         else:
-            raise ValueError("Invalid error type; must be one of [None, 'ucb2', 'ucb1']")
+            raise ValueError(f"Invalid error type {err_type}; must be one of [None, 'ucb2', 'ucb1']")
 
         res = self.summary()
         coeff = round(res.loc[res['treatment'] == tmt]['est'].values[0], 3)

From 4b5de446d148ecc0e266aa5852d931998c2fc824 Mon Sep 17 00:00:00 2001
From: Amar Venugopal <89877778+amarvenu@users.noreply.github.com>
Date: Wed, 24 Jan 2024 11:18:04 -0800
Subject: [PATCH 08/13] Update econml/validate/results.py

Co-authored-by: Keith Battocchi <kbattocchi@gmail.com>
Signed-off-by: Amar Venugopal <89877778+amarvenu@users.noreply.github.com>
---
 econml/validate/results.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/econml/validate/results.py b/econml/validate/results.py
index a76e705fb..a3c48442c 100644
--- a/econml/validate/results.py
+++ b/econml/validate/results.py
@@ -325,7 +325,7 @@ def plot_qini(self, tmt: int, err_type: str = None):
 
         err_type: str
             Type of error to plot. Accepted values are normal (None), two-sided uniform confidence band ('ucb2'),
-            or 1-sided uniform confidence band).
+            or 1-sided uniform confidence band ('ucb1').
 
         Returns
         -------

From dce622861801e12c1f38a3e4c43f9e9f1f6082d4 Mon Sep 17 00:00:00 2001
From: Amar Venugopal <89877778+amarvenu@users.noreply.github.com>
Date: Wed, 24 Jan 2024 11:18:10 -0800
Subject: [PATCH 09/13] Update econml/validate/results.py

Co-authored-by: Keith Battocchi <kbattocchi@gmail.com>
Signed-off-by: Amar Venugopal <89877778+amarvenu@users.noreply.github.com>
---
 econml/validate/results.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/econml/validate/results.py b/econml/validate/results.py
index a3c48442c..d2534da15 100644
--- a/econml/validate/results.py
+++ b/econml/validate/results.py
@@ -344,7 +344,7 @@ def plot_toc(self, tmt: int, err_type: str = None):
 
         err_type: str
             Type of error to plot. Accepted values are normal (None), two-sided uniform confidence band ('ucb2'),
-            or 1-sided uniform confidence band).
+            or 1-sided uniform confidence band ('ucb1').
 
         Returns
         -------

From 6dbdadbc54a0d31ad111b884451f51548e208460 Mon Sep 17 00:00:00 2001
From: Keith Battocchi <kebatt@microsoft.com>
Date: Mon, 18 Mar 2024 13:03:41 -0400
Subject: [PATCH 10/13] Fix 'DRtester' casing; add to API reference

Signed-off-by: Keith Battocchi <kebatt@microsoft.com>
---
 doc/reference.rst               | 14 ++++++++++++++
 econml/tests/test_drtester.py   | 12 ++++++------
 econml/validate/__init__.py     |  6 ++++--
 econml/validate/drtester.py     | 10 +++++++++-
 notebooks/CATE validation.ipynb | 10 +++++-----
 5 files changed, 38 insertions(+), 14 deletions(-)

diff --git a/doc/reference.rst b/doc/reference.rst
index daa00ea88..a86b91bf1 100644
--- a/doc/reference.rst
+++ b/doc/reference.rst
@@ -147,6 +147,20 @@ CATE Interpreters
     econml.cate_interpreter.SingleTreeCateInterpreter
     econml.cate_interpreter.SingleTreePolicyInterpreter
 
+.. _validation_api:
+
+CATE Validation
+---------------
+
+.. autosummary::
+    :toctree: _autosummary
+
+    econml.validation.DRTester
+    econml.validation.BLPEvaluationResults
+    econml.validation.CalibrationEvaluationResults
+    econml.validation.UpliftEvaluationResults
+    econml.validation.EvaluationResults
+
 .. _scorers_api:
 
 CATE Scorers
diff --git a/econml/tests/test_drtester.py b/econml/tests/test_drtester.py
index ec40ab17e..89ce1f0c4 100644
--- a/econml/tests/test_drtester.py
+++ b/econml/tests/test_drtester.py
@@ -5,7 +5,7 @@
 import scipy.stats as st
 from sklearn.ensemble import RandomForestClassifier, GradientBoostingRegressor
 
-from econml.validate.drtester import DRtester
+from econml.validate.drtester import DRTester
 from econml.dml import DML
 
 
@@ -70,7 +70,7 @@ def test_multi(self):
         ).fit(Y=Ytrain, T=Dtrain, X=Xtrain)
 
         # test the DR outcome difference
-        my_dr_tester = DRtester(
+        my_dr_tester = DRTester(
             model_regression=reg_y,
             model_propensity=reg_t,
             cate=cate
@@ -123,7 +123,7 @@ def test_binary(self):
         ).fit(Y=Ytrain, T=Dtrain, X=Xtrain)
 
         # test the DR outcome difference
-        my_dr_tester = DRtester(
+        my_dr_tester = DRTester(
             model_regression=reg_y,
             model_propensity=reg_t,
             cate=cate
@@ -171,7 +171,7 @@ def test_nuisance_val_fit(self):
         ).fit(Y=Ytrain, T=Dtrain, X=Xtrain)
 
         # test the DR outcome difference
-        my_dr_tester = DRtester(
+        my_dr_tester = DRTester(
             model_regression=reg_y,
             model_propensity=reg_t,
             cate=cate
@@ -212,7 +212,7 @@ def test_exceptions(self):
         ).fit(Y=Ytrain, T=Dtrain, X=Xtrain)
 
         # test the DR outcome difference
-        my_dr_tester = DRtester(
+        my_dr_tester = DRTester(
             model_regression=reg_y,
             model_propensity=reg_t,
             cate=cate
@@ -268,7 +268,7 @@ def test_exceptions(self):
             str(exc.exception) == "Unsupported metric - must be one of ['toc', 'qini']"
         )
 
-        my_dr_tester = DRtester(
+        my_dr_tester = DRTester(
             model_regression=reg_y,
             model_propensity=reg_t,
             cate=cate
diff --git a/econml/validate/__init__.py b/econml/validate/__init__.py
index a1c2adad7..d3cef7550 100644
--- a/econml/validate/__init__.py
+++ b/econml/validate/__init__.py
@@ -5,7 +5,9 @@
 A suite of validation methods for CATE models.
 """
 
-from .drtester import DRtester
+from .drtester import DRTester
+from .results import BLPEvaluationResults, CalibrationEvaluationResults, UpliftEvaluationResults, EvaluationResults
 
 
-__all__ = ['DRtester']
+__all__ = ['DRTester',
+           'BLPEvaluationResults', 'CalibrationEvaluationResults', 'UpliftEvaluationResults', 'EvaluationResults']
diff --git a/econml/validate/drtester.py b/econml/validate/drtester.py
index 5dd7d2f51..7b8b455f7 100644
--- a/econml/validate/drtester.py
+++ b/econml/validate/drtester.py
@@ -8,11 +8,13 @@
 from statsmodels.api import OLS
 from statsmodels.tools import add_constant
 
+from econml.utilities import deprecated
+
 from .results import CalibrationEvaluationResults, BLPEvaluationResults, UpliftEvaluationResults, EvaluationResults
 from .utils import calculate_dr_outcomes, calc_uplift
 
 
-class DRtester:
+class DRTester:
 
     """
     Validation tests for CATE models. Includes the best linear predictor (BLP) test as in Chernozhukov et al. (2022),
@@ -630,3 +632,9 @@ def evaluate_all(
         )
 
         return self.res
+
+
+@deprecated("DRtester has been renamed 'DRTester' and the old name has been deprecated and will be removed "
+            "in a future release. Please use 'DRTester' instead.")
+class DRtester(DRTester):
+    pass
diff --git a/notebooks/CATE validation.ipynb b/notebooks/CATE validation.ipynb
index c0b3c23a8..ecf36672a 100644
--- a/notebooks/CATE validation.ipynb	
+++ b/notebooks/CATE validation.ipynb	
@@ -23,7 +23,7 @@
     "from econml.metalearners import TLearner\n",
     "from econml.dml import DML\n",
     "\n",
-    "from econml.validate.drtester import DRtester"
+    "from econml.validate.drtester import DRTester"
    ]
   },
   {
@@ -244,8 +244,8 @@
     }
    ],
    "source": [
-    "# Initialize DRtester and fit/predict nuisance models\n",
-    "dml_tester = DRtester(\n",
+    "# Initialize DRTester and fit/predict nuisance models\n",
+    "dml_tester = DRTester(\n",
     "    model_regression=model_regression, \n",
     "    model_propensity=model_propensity, \n",
     "    cate=est_dm\n",
@@ -605,8 +605,8 @@
     }
    ],
    "source": [
-    "# Initialize DRtester and fit/predict nuisance models\n",
-    "t_tester = DRtester(\n",
+    "# Initialize DRTester and fit/predict nuisance models\n",
+    "t_tester = DRTester(\n",
     "    model_regression=model_regression, \n",
     "    model_propensity=model_propensity, \n",
     "    cate=est_t\n",

From 49b8b9d207544987edc460edcbdd026bfe001546 Mon Sep 17 00:00:00 2001
From: Keith Battocchi <kebatt@microsoft.com>
Date: Tue, 19 Mar 2024 00:43:07 -0400
Subject: [PATCH 11/13] Fix tests

Signed-off-by: Keith Battocchi <kebatt@microsoft.com>
---
 econml/tests/test_drtester.py | 30 +++++++++++++++---------------
 econml/validate/results.py    |  6 +++++-
 econml/validate/utils.py      |  2 +-
 3 files changed, 21 insertions(+), 17 deletions(-)

diff --git a/econml/tests/test_drtester.py b/econml/tests/test_drtester.py
index 89ce1f0c4..3396f0fe2 100644
--- a/econml/tests/test_drtester.py
+++ b/econml/tests/test_drtester.py
@@ -193,8 +193,8 @@ def test_nuisance_val_fit(self):
         for kwargs in [{}, {'Xval': Xval}]:
             with self.assertRaises(Exception) as exc:
                 my_dr_tester.evaluate_cal(kwargs)
-            self.assertTrue(
-                str(exc.exception) == "Must fit nuisance models on training sample data to use calibration test"
+            self.assertEqual(
+                str(exc.exception), "Must fit nuisance models on training sample data to use calibration test"
             )
 
     def test_exceptions(self):
@@ -223,11 +223,11 @@ def test_exceptions(self):
             with self.assertRaises(Exception) as exc:
                 func()
             if func.__name__ == 'evaluate_cal':
-                self.assertTrue(
-                    str(exc.exception) == "Must fit nuisance models on training sample data to use calibration test"
+                self.assertEqual(
+                    str(exc.exception), "Must fit nuisance models on training sample data to use calibration test"
                 )
             else:
-                self.assertTrue(str(exc.exception) == "Must fit nuisances before evaluating")
+                self.assertEqual(str(exc.exception), "Must fit nuisances before evaluating")
 
         my_dr_tester = my_dr_tester.fit_nuisance(
             Xval, Dval, Yval, Xtrain, Dtrain, Ytrain
@@ -242,12 +242,12 @@ def test_exceptions(self):
             with self.assertRaises(Exception) as exc:
                 func()
             if func.__name__ == 'evaluate_blp':
-                self.assertTrue(
-                    str(exc.exception) == "CATE predictions not yet calculated - must provide Xval"
+                self.assertEqual(
+                    str(exc.exception), "CATE predictions not yet calculated - must provide Xval"
                 )
             else:
-                self.assertTrue(str(exc.exception) ==
-                                "CATE predictions not yet calculated - must provide both Xval, Xtrain")
+                self.assertEqual(str(exc.exception),
+                                 "CATE predictions not yet calculated - must provide both Xval, Xtrain")
 
         for func in [
             my_dr_tester.evaluate_cal,
@@ -256,16 +256,16 @@ def test_exceptions(self):
         ]:
             with self.assertRaises(Exception) as exc:
                 func(Xval=Xval)
-            self.assertTrue(
-                str(exc.exception) == "CATE predictions not yet calculated - must provide both Xval, Xtrain")
+            self.assertEqual(
+                str(exc.exception), "CATE predictions not yet calculated - must provide both Xval, Xtrain")
 
         cal_res = my_dr_tester.evaluate_cal(Xval, Xtrain)
         self.assertGreater(cal_res.cal_r_squared[0], 0)  # good R2
 
         with self.assertRaises(Exception) as exc:
             my_dr_tester.evaluate_uplift(metric='blah')
-        self.assertTrue(
-            str(exc.exception) == "Unsupported metric - must be one of ['toc', 'qini']"
+        self.assertEqual(
+            str(exc.exception), "Unsupported metric 'blah' - must be one of ['toc', 'qini']"
         )
 
         my_dr_tester = DRTester(
@@ -280,8 +280,8 @@ def test_exceptions(self):
 
         with self.assertRaises(Exception) as exc:
             qini_res.plot_uplift(tmt=1, err_type='blah')
-        self.assertTrue(
-            str(exc.exception) == "Invalid error type; must be one of [None, 'ucb2', 'ucb1']"
+        self.assertEqual(
+            str(exc.exception), "Invalid error type 'blah'; must be one of [None, 'ucb2', 'ucb1']"
         )
 
         autoc_res = my_dr_tester.evaluate_uplift(Xval, Xtrain, metric='toc')
diff --git a/econml/validate/results.py b/econml/validate/results.py
index d2534da15..7a2390e03 100644
--- a/econml/validate/results.py
+++ b/econml/validate/results.py
@@ -20,6 +20,7 @@ class CalibrationEvaluationResults:
     treatments: list or numpy array of floats
         Sequence of treatment labels
     """
+
     def __init__(
         self,
         cal_r_squared: np.array,
@@ -99,6 +100,7 @@ class BLPEvaluationResults:
     treatments: list or numpy array of floats
        Sequence of treatment labels
     """
+
     def __init__(
         self,
         params: List[float],
@@ -154,6 +156,7 @@ class UpliftEvaluationResults:
         Dictionary mapping treatment levels to dataframes containing
         necessary data for plotting uplift curves
     """
+
     def __init__(
         self,
         params: List[float],
@@ -217,7 +220,7 @@ def plot_uplift(self, tmt: Any, err_type: str = None):
         elif err_type == 'ucb1':
             df['95_err'] = df['uniform_one_side_critical_value'] * df['err']
         else:
-            raise ValueError(f"Invalid error type {err_type}; must be one of [None, 'ucb2', 'ucb1']")
+            raise ValueError(f"Invalid error type {err_type!r}; must be one of [None, 'ucb2', 'ucb1']")
 
         res = self.summary()
         coeff = round(res.loc[res['treatment'] == tmt]['est'].values[0], 3)
@@ -263,6 +266,7 @@ class EvaluationResults:
     toc_res: UpliftEvaluationResults object
        Results object for TOC test
     """
+
     def __init__(
         self,
         cal_res: CalibrationEvaluationResults,
diff --git a/econml/validate/utils.py b/econml/validate/utils.py
index 159c18a1d..2103ab4f1 100644
--- a/econml/validate/utils.py
+++ b/econml/validate/utils.py
@@ -99,7 +99,7 @@ def calc_uplift(
             toc[it] = np.mean(dr_val[inds]) - ate  # tau(q) := E[Y(1) - Y(0) | tau(X) >= q[it]] - E[Y(1) - Y(0)]
             toc_psi[it, :] = np.squeeze((dr_val - ate) * (inds / group_prob - 1) - toc[it])
         else:
-            raise ValueError("Unsupported metric - must be one of ['toc', 'qini']")
+            raise ValueError(f"Unsupported metric {metric!r} - must be one of ['toc', 'qini']")
 
         toc_std[it] = np.sqrt(np.mean(toc_psi[it] ** 2) / n)  # standard error of tau(q)
 

From 27606f3f0aea65afc2da1e9277a252e52bb008bf Mon Sep 17 00:00:00 2001
From: Keith Battocchi <kebatt@microsoft.com>
Date: Tue, 19 Mar 2024 09:14:51 -0400
Subject: [PATCH 12/13] Fix module name in docs

Signed-off-by: Keith Battocchi <kebatt@microsoft.com>
---
 doc/reference.rst | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/doc/reference.rst b/doc/reference.rst
index a86b91bf1..f763e82c7 100644
--- a/doc/reference.rst
+++ b/doc/reference.rst
@@ -155,11 +155,11 @@ CATE Validation
 .. autosummary::
     :toctree: _autosummary
 
-    econml.validation.DRTester
-    econml.validation.BLPEvaluationResults
-    econml.validation.CalibrationEvaluationResults
-    econml.validation.UpliftEvaluationResults
-    econml.validation.EvaluationResults
+    econml.validate.DRTester
+    econml.validate.BLPEvaluationResults
+    econml.validate.CalibrationEvaluationResults
+    econml.validate.UpliftEvaluationResults
+    econml.validate.EvaluationResults
 
 .. _scorers_api:
 

From 94e5ccfb2e62a2cf417f29289e312108c86b11b5 Mon Sep 17 00:00:00 2001
From: Keith Battocchi <kebatt@microsoft.com>
Date: Tue, 19 Mar 2024 10:17:08 -0400
Subject: [PATCH 13/13] Fix docstrings

Signed-off-by: Keith Battocchi <kebatt@microsoft.com>
---
 econml/validate/drtester.py | 57 ++++++++++++++++++-------------------
 1 file changed, 28 insertions(+), 29 deletions(-)

diff --git a/econml/validate/drtester.py b/econml/validate/drtester.py
index 7b8b455f7..84c58ba95 100644
--- a/econml/validate/drtester.py
+++ b/econml/validate/drtester.py
@@ -15,7 +15,6 @@
 
 
 class DRTester:
-
     """
     Validation tests for CATE models. Includes the best linear predictor (BLP) test as in Chernozhukov et al. (2022),
     the calibration test in Dwivedi et al. (2020), and the QINI coefficient as in Radcliffe (2007).
@@ -86,12 +85,12 @@ class DRTester:
     Parameters
     ----------
     model_regression: estimator
-        Nuisance model estimator used to fit the outcome to features. Must be able to implement `fit' and `predict'
+        Nuisance model estimator used to fit the outcome to features. Must be able to implement `fit` and `predict`
         methods
 
     model_propensity: estimator
-        Nuisance model estimator used to fit the treatment assignment to features. Must be able to implement `fit'
-        method and either `predict' (in the case of binary treatment) or `predict_proba' methods (in the case of
+        Nuisance model estimator used to fit the treatment assignment to features. Must be able to implement `fit`
+        method and either `predict` (in the case of binary treatment) or `predict_proba` methods (in the case of
         multiple categorical treatments).
 
     cate: estimator
@@ -191,7 +190,7 @@ def fit_nuisance(
         Generates nuisance predictions and calculates doubly robust (DR) outcomes either by (1) cross-fitting in the
         validation sample, or (2) fitting in the training sample and applying to the validation sample. If Xtrain,
         Dtrain, and ytrain are all not None, then option (2) will be implemented, otherwise, option (1) will be
-        implemented. In order to use the `evaluate_cal' method then Xtrain, Dtrain, and ytrain must all be specified.
+        implemented. In order to use the `evaluate_cal` method then Xtrain, Dtrain, and ytrain must all be specified.
 
         Parameters
         ----------
@@ -202,12 +201,12 @@ def fit_nuisance(
             the control status be equal to 0, and all other treatments integers starting at 1.
         yval: vector of length n_val
             Outcomes for the validation sample
-        Xtrain: (n_train x k) matrix or vector of length n, default ``None``
+        Xtrain: (n_train x k) matrix or vector of length n, optional
             Features used in nuisance models for training sample
-        Dtrain: vector of length n_train, default ``None''
+        Dtrain: vector of length n_train, optional
             Treatment assignment of training sample. Control status must be minimum value. It is recommended to have
             the control status be equal to 0, and all other treatments integers starting at 1.
-        ytrain: vector of length n_train, defaul ``None``
+        ytrain: vector of length n_train, optional
             Outcomes for the training sample
 
         Returns
@@ -348,7 +347,7 @@ def get_cate_preds(
         ----------
         Xval: (n_val x n_treatment) matrix
             Validation set features to be used to predict (and potentially fit) DR outcomes in CATE model
-        Xtrain (n_train x n_treatment) matrix, defaul ``None``
+        Xtrain (n_train x n_treatment) matrix, optional
             Training set features used to fit CATE model
 
         Returns
@@ -375,11 +374,11 @@ def evaluate_cal(
 
         Parameters
         ----------
-        Xval: (n_val x n_treatment) matrix, default ``None``
-            Validation sample features for CATE model. If not specified, then `fit_cate' method must already have been
+        Xval: (n_val x n_treatment) matrix, optional
+            Validation sample features for CATE model. If not specified, then `fit_cate` method must already have been
             implemented
-        Xtrain: (n_train x n_treatment) matrix, default ``None``
-            Training sample features for CATE model. If not specified, then `fit cate' method must already have been
+        Xtrain: (n_train x n_treatment) matrix, optional
+            Training sample features for CATE model. If not specified, then `fit cate` method must already have been
             implemented (with Xtrain specified)
         n_groups: integer, default 4
             Number of quantile-based groups used to calculate calibration score.
@@ -449,17 +448,17 @@ def evaluate_blp(
         Xtrain: np.array = None
     ) -> BLPEvaluationResults:
         """
-        Implements the best linear predictor (BLP) test as in [Chernozhukov2022]. `fit_nusiance' method must already
+        Implements the best linear predictor (BLP) test as in [Chernozhukov2022]. `fit_nusiance` method must already
         be implemented.
 
         Parameters
         ----------
-        Xval: (n_val x k) matrix, default ``None''
-            Validation sample features for CATE model. If not specified, then `fit_cate' method must already have been
+        Xval: (n_val x k) matrix, optional
+            Validation sample features for CATE model. If not specified, then `fit_cate` method must already have been
             implemented
-        Xtrain: (n_train x k) matrix, default ``None''
+        Xtrain: (n_train x k) matrix, optional
             Training sample features for CATE model. If specified, then CATE is fitted on training sample and applied
-            to Xval. If specified, then Xtrain, Dtrain, Ytrain must have been specified in `fit_nuisance' method (and
+            to Xval. If specified, then Xtrain, Dtrain, Ytrain must have been specified in `fit_nuisance` method (and
             vice-versa)
 
         Returns
@@ -517,14 +516,14 @@ def evaluate_uplift(
 
         Parameters
         ----------
-        Xval: (n_val x k) matrix, default ``None''
-            Validation sample features for CATE model. If not specified, then `fit_cate' method must already have been
+        Xval: (n_val x k) matrix, optional
+            Validation sample features for CATE model. If not specified, then `fit_cate` method must already have been
             implemented
-        Xtrain: (n_train x k) matrix, default ``None''
+        Xtrain: (n_train x k) matrix, optional
             Training sample features for CATE model. If specified, then CATE is fitted on training sample and applied
-            to Xval. If specified, then Xtrain, Dtrain, Ytrain must have been specified in `fit_nuisance' method (and
+            to Xval. If specified, then Xtrain, Dtrain, Ytrain must have been specified in `fit_nuisance` method (and
             vice-versa)
-        percentiles: one-dimensional array, default ``np.linspace(5, 95, 50)''
+        percentiles: one-dimensional array, default ``np.linspace(5, 95, 50)``
             Array of percentiles over which the QINI curve should be constructed. Defaults to 5%-95% in intervals of
             5%.
         metric: string, default 'qini'
@@ -593,16 +592,16 @@ def evaluate_all(
         n_bootstrap: int = 1000
     ) -> EvaluationResults:
         """
-        Implements the best linear prediction (`evaluate_blp'), calibration (`evaluate_cal'), uplift curve
-        ('evaluate_uplift') methods
+        Implements the best linear prediction (`evaluate_blp`), calibration (`evaluate_cal`), uplift curve
+        (`evaluate_uplift`) methods
 
         Parameters
         ----------
-        Xval: (n_cal x k) matrix, default ``None''
-            Validation sample features for CATE model. If not specified, then `fit_cate' method must already have been
+        Xval: (n_cal x k) matrix, optional
+            Validation sample features for CATE model. If not specified, then `fit_cate` method must already have been
             implemented
-        Xtrain: (n_train x k) matrix, default ``None''
-            Training sample features for CATE model. If not specified, then `fit_cate' method must already have been
+        Xtrain: (n_train x k) matrix, optional
+            Training sample features for CATE model. If not specified, then `fit_cate` method must already have been
             implemented
         n_groups: integer, default 4
             Number of quantile-based groups used to calculate calibration score.