Fix E731

Signed-off-by: Keith Battocchi <kebatt@microsoft.com>

notebooks/AutomatedML/Automated Machine Learning For EconML.ipynb

@@ -310,11 +310,13 @@
     "# Outcome support\n",
     "support_Y = np.random.choice(np.arange(n_w), size=support_size, replace=False)\n",
     "coefs_Y = np.random.uniform(0, 1, size=support_size)\n",
-    "epsilon_sample = lambda n: np.random.uniform(-1, 1, size=n)\n",
+    "def epsilon_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n)\n",
     "# Treatment support\n",
     "support_T = support_Y\n",
     "coefs_T = np.random.uniform(0, 1, size=support_size)\n",
-    "eta_sample = lambda n: np.random.uniform(-1, 1, size=n)\n",
+    "def eta_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n)\n",
     "\n",
     "# Generate controls, covariates, treatments and outcomes\n",
     "W = np.random.normal(0, 1, size=(n, n_w))\n",

notebooks/Causal Forest and Orthogonal Random Forest Examples.ipynb

@@ -125,11 +125,13 @@
     "# Outcome support\n",
     "support_Y = np.random.choice(range(n_w), size=support_size, replace=False)\n",
     "coefs_Y = np.random.uniform(0, 1, size=support_size)\n",
-    "epsilon_sample = lambda n: np.random.uniform(-1, 1, size=n)\n",
+    "def epsilon_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n)\n",
     "# Treatment support \n",
     "support_T = support_Y\n",
     "coefs_T = np.random.uniform(0, 1, size=support_size)\n",
-    "eta_sample = lambda n: np.random.uniform(-1, 1, size=n) \n",
+    "def eta_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n) \n",
     "\n",
     "# Generate controls, covariates, treatments and outcomes\n",
     "W = np.random.normal(0, 1, size=(n, n_w))\n",
@@ -552,11 +554,13 @@
     "# Outcome support\n",
     "support_Y = np.random.choice(range(n_w), size=support_size, replace=False)\n",
     "coefs_Y = np.random.uniform(0, 1, size=support_size)\n",
-    "epsilon_sample = lambda n: np.random.uniform(-1, 1, size=n)\n",
+    "def epsilon_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n)\n",
     "# Treatment support\n",
     "support_T = support_Y\n",
     "coefs_T = np.random.uniform(0, 1, size=support_size)\n",
-    "eta_sample = lambda n: np.random.uniform(-1, 1, size=n) \n",
+    "def eta_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n) \n",
     "\n",
     "# Generate controls, covariates, treatments and outcomes\n",
     "W = np.random.normal(0, 1, size=(n, n_w))\n",
@@ -895,11 +899,13 @@
     "    # Outcome support\n",
     "    support_Y = np.random.choice(range(n_w), size=support_size, replace=False)\n",
     "    coefs_Y = np.random.uniform(0, 1, size=support_size)\n",
-    "    epsilon_sample = lambda n: np.random.uniform(-1, 1, size=n)\n",
+    "    def epsilon_sample(n):\n",
+    "        return np.random.uniform(-1, 1, size=n)\n",
     "    # Treatment support \n",
     "    support_T = support_Y\n",
     "    coefs_T = np.random.uniform(0, 1, size=(support_size, n_treatments))\n",
-    "    eta_sample = lambda n: np.random.uniform(-1, 1, size=n) \n",
+    "    def eta_sample(n):\n",
+    "        return np.random.uniform(-1, 1, size=n) \n",
     "    # Generate controls, covariates, treatments and outcomes\n",
     "    W = np.random.normal(0, 1, size=(n, n_w))\n",
     "    X = np.random.uniform(0, 1, size=(n, n_x))\n",

notebooks/Causal Model Selection with the RScorer.ipynb

@@ -119,11 +119,13 @@
     "# Outcome support\n",
     "support_Y = np.random.choice(range(n_x), size=support_size, replace=False)\n",
     "coefs_Y = np.random.uniform(0, 1, size=support_size)\n",
-    "epsilon_sample = lambda n:np.random.uniform(-1, 1, size=n)\n",
+    "def epsilon_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n)\n",
     "# Treatment support\n",
     "support_T = support_Y\n",
     "coefs_T = np.random.uniform(0, 1, size=support_size)\n",
-    "eta_sample = lambda n: np.random.uniform(-1, 1, size=n) \n",
+    "def eta_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n) \n",
     "\n",
     "# Generate controls, covariates, treatments and outcomes\n",
     "X = np.random.uniform(0, 1, size=(n, n_x))\n",
@@ -155,8 +157,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "reg = lambda: RandomForestRegressor(min_samples_leaf=10)\n",
+    "def reg():\n",
-    "clf = lambda: RandomForestClassifier(min_samples_leaf=10)"
+    "    return RandomForestRegressor(min_samples_leaf=10)\n",
+    "def clf():\n",
+    "    return RandomForestClassifier(min_samples_leaf=10)"
    ]
   },
   {
@@ -421,8 +425,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "reg = lambda: RandomForestRegressor(min_samples_leaf=10, random_state=123)\n",
+    "def reg():\n",
-    "clf = lambda: RandomForestClassifier(min_samples_leaf=10, random_state=123)"
+    "    return RandomForestRegressor(min_samples_leaf=10, random_state=123)\n",
+    "def clf():\n",
+    "    return RandomForestClassifier(min_samples_leaf=10, random_state=123)"
    ]
   },
   {

notebooks/Choosing First Stage Models.ipynb

@@ -83,7 +83,8 @@
     "p = 10\n",
     "W = np.random.uniform(size=(n, p))\n",
     "X = np.random.uniform(size=(n, 1))\n",
-    "true_effect = lambda x: x[:, 0] ** 2\n",
+    "def true_effect(x):\n",
+    "    return x[:, 0] ** 2\n",
     "T = W[:, 0] + W[:, 1] ** 2 + np.random.uniform(-1, 1, size=n)\n",
     "Y = (\n",
     "    true_effect(X) * T\n",
@@ -158,12 +159,8 @@
     }
    ],
    "source": [
-    "first_stage = lambda: GridSearchCV(\n",
+    "def first_stage():\n",
-    "    estimator=GradientBoostingRegressor(),\n",
+    "    return GridSearchCV(estimator=GradientBoostingRegressor(), param_grid={\"max_depth\": [3, 5, None], \"n_estimators\": (50, 100, 200)}, cv=2, n_jobs=-1)\n",
-    "    param_grid={\"max_depth\": [3, 5, None], \"n_estimators\": (50, 100, 200)},\n",
-    "    cv=2,\n",
-    "    n_jobs=-1,\n",
-    ")\n",
     "est = LinearDML(\n",
     "    model_y=first_stage(),\n",
     "    model_t=first_stage(),\n",
@@ -381,14 +378,8 @@
     }
    ],
    "source": [
-    "first_stage = lambda: GridSearchCVList(\n",
+    "def first_stage():\n",
-    "    [Lasso(max_iter=10000), GradientBoostingRegressor()],\n",
+    "    return GridSearchCVList([Lasso(max_iter=10000), GradientBoostingRegressor()], param_grid_list=[{\"alpha\": [0.001, 0.01, 0.1, 1, 10]}, {\"max_depth\": [3, 5, None], \"n_estimators\": [50, 100, 200]}], cv=2)"
-    "    param_grid_list=[\n",
-    "        {\"alpha\": [0.001, 0.01, 0.1, 1, 10]},\n",
-    "        {\"max_depth\": [3, 5, None], \"n_estimators\": [50, 100, 200]},\n",
-    "    ],\n",
-    "    cv=2,\n",
-    ")"
    ]
   },
   {

notebooks/CustomerScenarios/Case Study - Multi-investment Attribution at A Software Company - EconML + DoWhy.ipynb

@@ -397,7 +397,8 @@
    "outputs": [],
    "source": [
     "# Define underlying treatment effect function\n",
-    "TE_fn = lambda X: np.hstack([5000 + 2 / 100 * X, 5 / 100 * X])\n",
+    "def TE_fn(X):\n",
+    "    return np.hstack([5000 + 2 / 100 * X, 5 / 100 * X])\n",
     "true_TE = TE_fn(X)\n",
     "\n",
     "# Define true coefficients for the three treatments\n",

notebooks/CustomerScenarios/Case Study - Recommendation AB Testing at An Online Travel Company - EconML + DoWhy.ipynb

@@ -369,7 +369,8 @@
    "outputs": [],
    "source": [
     "# Define underlying treatment effect function \n",
-    "TE_fn = lambda X: (0.2 + 0.3 * X['days_visited_free_pre'] - 0.2 * X['days_visited_hs_pre'] + X['os_type_osx']).values\n",
+    "def TE_fn(X):\n",
+    "    return (0.2 + 0.3 * X['days_visited_free_pre'] - 0.2 * X['days_visited_hs_pre'] + X['os_type_osx']).values\n",
     "true_TE = TE_fn(X_data)\n",
     "\n",
     "# Define the true coefficients to compare with\n",

notebooks/Double Machine Learning Examples.ipynb

@@ -139,11 +139,13 @@
     "# Outcome support\n",
     "support_Y = np.random.choice(np.arange(n_w), size=support_size, replace=False)\n",
     "coefs_Y = np.random.uniform(0, 1, size=support_size)\n",
-    "epsilon_sample = lambda n: np.random.uniform(-1, 1, size=n)\n",
+    "def epsilon_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n)\n",
     "# Treatment support\n",
     "support_T = support_Y\n",
     "coefs_T = np.random.uniform(0, 1, size=support_size)\n",
-    "eta_sample = lambda n: np.random.uniform(-1, 1, size=n)\n",
+    "def eta_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n)\n",
     "\n",
     "# Generate controls, covariates, treatments and outcomes\n",
     "W = np.random.normal(0, 1, size=(n, n_w))\n",
@@ -769,11 +771,13 @@
     "# Outcome support\n",
     "support_Y = np.random.choice(range(n_w), size=support_size, replace=False)\n",
     "coefs_Y = np.random.uniform(0, 1, size=support_size)\n",
-    "epsilon_sample = lambda n:np.random.uniform(-1, 1, size=n)\n",
+    "def epsilon_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n)\n",
     "# Treatment support\n",
     "support_T = support_Y\n",
     "coefs_T = np.random.uniform(0, 1, size=support_size)\n",
-    "eta_sample = lambda n: np.random.uniform(-1, 1, size=n) \n",
+    "def eta_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n) \n",
     "\n",
     "# Generate controls, covariates, treatments and outcomes\n",
     "W = np.random.normal(0, 1, size=(n, n_w))\n",
@@ -1632,11 +1636,13 @@
     "# Outcome support\n",
     "support_Y = np.random.choice(np.arange(n_w), size=support_size, replace=False)\n",
     "coefs_Y = np.random.uniform(0, 1, size=support_size)\n",
-    "epsilon_sample = lambda n: np.random.uniform(-1, 1, size=n)\n",
+    "def epsilon_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n)\n",
     "# Treatment support\n",
     "support_T = support_Y\n",
     "coefs_T = np.random.uniform(0, 1, size=support_size)\n",
-    "eta_sample = lambda n: np.random.uniform(-1, 1, size=n)\n",
+    "def eta_sample(n):\n",
+    "    return np.random.uniform(-1, 1, size=n)\n",
     "\n",
     "# Generate controls, covariates, treatments and outcomes\n",
     "W = np.random.normal(0, 1, size=(n, n_w))\n",

notebooks/ForestLearners Basic Example.ipynb

@@ -66,9 +66,12 @@
     "n = 2000\n",
     "p = 10\n",
     "X = np.random.normal(size=(n, p))\n",
-    "true_propensity = lambda x: .4 + .2 * (x[:, 0] > 0)\n",
+    "def true_propensity(x):\n",
-    "true_effect = lambda x: (x[:, 0] * (x[:, 0] > 0))\n",
+    "    return 0.4 + 0.2 * (x[:, 0] > 0)\n",
-    "true_conf = lambda x: x[:, 1] + np.clip(x[:, 2], - np.inf, 0)\n",
+    "def true_effect(x):\n",
+    "    return x[:, 0] * (x[:, 0] > 0)\n",
+    "def true_conf(x):\n",
+    "    return x[:, 1] + np.clip(x[:, 2], -np.inf, 0)\n",
     "T = np.random.binomial(1, true_propensity(X))\n",
     "Y =  true_effect(X) * T + true_conf(X) + np.random.normal(size=(n,))"
    ]

notebooks/Generalized Random Forests.ipynb

@@ -84,8 +84,8 @@
     "n_treatments = 1\n",
     "# true_te = lambda X: np.hstack([X[:, [0]]**2 + 1, np.ones((X.shape[0], n_treatments - 1))])\n",
     "# true_te = lambda X: np.hstack([X[:, [0]]>0, np.ones((X.shape[0], n_treatments - 1))])\n",
-    "true_te = lambda X: np.hstack([(X[:, [0]]>0) * X[:, [0]],\n",
+    "def true_te(X):\n",
-    "                               np.ones((X.shape[0], n_treatments - 1))*np.arange(1, n_treatments).reshape(1, -1)])\n",
+    "    return np.hstack([(X[:, [0]] > 0) * X[:, [0]], np.ones((X.shape[0], n_treatments - 1)) * np.arange(1, n_treatments).reshape(1, -1)])\n",
     "X = np.random.normal(0, 1, size=(n_samples, n_features))\n",
     "T = np.random.normal(0, 1, size=(n_samples, n_treatments))\n",
     "for t in range(n_treatments):\n",
@@ -378,7 +378,8 @@
     "n_features = 10\n",
     "n_treatments = 2\n",
     "# true_te = lambda X: np.hstack([X[:, [0]]**2 + 1, np.ones((X.shape[0], n_treatments - 1))])\n",
-    "true_te = lambda X: np.hstack([X[:, [0]]>0, np.ones((X.shape[0], n_treatments - 1))])\n",
+    "def true_te(X):\n",
+    "    return np.hstack([X[:, [0]] > 0, np.ones((X.shape[0], n_treatments - 1))])\n",
     "# true_te = lambda X: np.hstack([(X[:, [0]]>0) * X[:, [0]],\n",
     "#                                np.ones((X.shape[0], n_treatments - 1))*np.arange(1, n_treatments).reshape(1, -1)])\n",
     "Z = np.random.normal(0, 1, size=(n_samples, n_treatments))\n",
@@ -616,7 +617,8 @@
     "n_samples = 2000\n",
     "n_features = 10\n",
     "n_outputs = 2\n",
-    "true_te = lambda X: np.hstack([X[:, [0]]**2 + 1, np.ones((X.shape[0], n_outputs - 1))])\n",
+    "def true_te(X):\n",
+    "    return np.hstack([X[:, [0]] ** 2 + 1, np.ones((X.shape[0], n_outputs - 1))])\n",
     "# true_te = lambda X: np.hstack([X[:, [0]]>0, np.ones((X.shape[0], n_outputs - 1))])\n",
     "# true_te = lambda X: np.hstack([(X[:, [0]]>0) * X[:, [0]],\n",
     "#                                np.ones((X.shape[0], n_outputs - 1))*np.arange(1, n_outputs).reshape(1, -1)])\n",
@@ -808,8 +810,8 @@
     "n_outputs = 2\n",
     "# true_te = lambda X: np.hstack([X[:, [0]]**2 + 1, np.ones((X.shape[0], n_treatments - 1))])\n",
     "# true_te = lambda X: np.hstack([X[:, [0]]>0, np.ones((X.shape[0], n_treatments - 1))])\n",
-    "true_te = lambda X: np.hstack([(X[:, [0]]>0) * X[:, [0]],\n",
+    "def true_te(X):\n",
-    "                               np.ones((X.shape[0], n_treatments - 1))*np.arange(1, n_treatments).reshape(1, -1)])\n",
+    "    return np.hstack([(X[:, [0]] > 0) * X[:, [0]], np.ones((X.shape[0], n_treatments - 1)) * np.arange(1, n_treatments).reshape(1, -1)])\n",
     "X = np.random.normal(0, 1, size=(n_samples, n_features))\n",
     "W = np.random.normal(0, 1, size=(n_samples, n_features))\n",
     "T = np.random.normal(0, 1, size=(n_samples, n_treatments))\n",
@@ -1459,7 +1461,8 @@
     "n_samples = 2000\n",
     "n_features = 10\n",
     "n_treatments = 2\n",
-    "true_te = lambda X: np.hstack([X[:, [0]]>0, np.ones((X.shape[0], n_treatments - 1))])\n",
+    "def true_te(X):\n",
+    "    return np.hstack([X[:, [0]] > 0, np.ones((X.shape[0], n_treatments - 1))])\n",
     "Z = np.random.normal(0, 1, size=(n_samples, n_treatments))\n",
     "X = np.random.normal(0, 1, size=(n_samples, n_features))\n",
     "U = np.random.normal(0, .2, size=(n_samples, 1))\n",

notebooks/Interpretability with SHAP.ipynb

@@ -69,7 +69,8 @@
     "np.random.seed(123)\n",
     "n_samples = 5000\n",
     "n_features = 10\n",
-    "true_te = lambda X: (X[:, 0]>0) * X[:, 0]\n",
+    "def true_te(X):\n",
+    "    return (X[:, 0] > 0) * X[:, 0]\n",
     "X = np.random.normal(0, 1, size=(n_samples, n_features))\n",
     "W = np.random.normal(0, 1, size=(n_samples, n_features))\n",
     "T = np.random.binomial(1, scipy.special.expit(X[:, 0]))\n",
@@ -293,8 +294,8 @@
     "n_features = 10\n",
     "n_treatments = 2\n",
     "n_outputs = 3\n",
-    "true_te = lambda X: np.hstack([(X[:, [0]]>0) * X[:, [0]],\n",
+    "def true_te(X):\n",
-    "                               np.ones((X.shape[0], n_treatments - 1))*np.arange(1, n_treatments).reshape(1, -1)])\n",
+    "    return np.hstack([(X[:, [0]] > 0) * X[:, [0]], np.ones((X.shape[0], n_treatments - 1)) * np.arange(1, n_treatments).reshape(1, -1)])\n",
     "X = np.random.normal(0, 1, size=(n_samples, n_features))\n",
     "W = np.random.normal(0, 1, size=(n_samples, n_features))\n",
     "T = np.random.normal(0, 1, size=(n_samples, n_treatments))\n",

notebooks/OrthoIV and DRIV Examples.ipynb

@@ -195,7 +195,8 @@
     }
    ],
    "source": [
-    "func = lambda X: 10\n",
+    "def func(X):\n",
+    "    return 10\n",
     "n = 5000\n",
     "p = 10\n",
     "y, T, Z, X = dgp(n, p, func)"
@@ -241,8 +242,10 @@
     }
    ],
    "source": [
-    "model = lambda: LinearRegression()\n",
+    "def model():\n",
-    "model_clf = lambda: LogisticRegression()"
+    "    return LinearRegression()\n",
+    "def model_clf():\n",
+    "    return LogisticRegression()"
    ]
   },
   {
@@ -732,7 +735,8 @@
     }
    ],
    "source": [
-    "func = lambda X: 10 * X[:, 0]"
+    "def func(X):\n",
+    "    return 10 * X[:, 0]"
    ]
   },
   {

pyproject.toml

@@ -155,7 +155,6 @@ ignore = [
     "E402", # Module level import not at top of file
     "E713", # Test for membership should be 'not in'
     "E722", # Do not use bare 'except'
-    "E731", # Do not assign a lambda expression, use a def
     "D100", # Missing docstring in public module
     "D101", # Missing docstring in public class
     "D102", # Missing docstring in public method