fixed typos

Author: DvirDukhan

notebooks/shapley_explainability/XGBoostGenericShapleyFraudDetection.ipynb

@@ -39,7 +39,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -75,7 +75,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -228,7 +228,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -443,7 +443,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -461,27 +461,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "with open(\"models/fraud_detection_model.pt\", \"rb\") as f:\n",
     "    fraud_detection_model_blob = f.read()\n",
     "\n",
-    "with open(\"torch_shapely.py\", \"rb\") as f:\n",
+    "with open(\"torch_shapley.py\", \"rb\") as f:\n",
     "    shapely_script = f.read()"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We load both movel and script into RedisAI."
+    "We load both model and script into RedisAI."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -490,14 +490,14 @@
        "'OK'"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "rai.modelstore(\"fraud_detection_model\", \"TORCH\", \"CPU\", fraud_detection_model_blob)\n",
-    "rai.scriptstore(\"shapely_script\", device='CPU', script=shapely_script, entry_points=[\"shapely_sample\"] )"
+    "rai.scriptstore(\"shapley_script\", device='CPU', script=shapely_script, entry_points=[\"shapley_sample\"] )"
    ]
   },
   {
@@ -509,7 +509,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -523,7 +523,7 @@
    "source": [
     "rai.tensorset(\"fraud_input\", X_test_fraud, dtype=\"float\")\n",
     "\n",
-    "rai.scriptexecute(\"shapely_script\", \"shapely_sample\", inputs = [\"fraud_input\"], keys = [\"fraud_detection_model\"], args = [\"20\", \"2\", \"0\"], outputs=[\"fraud_explanations\"])\n",
+    "rai.scriptexecute(\"shapley_script\", \"shapley_sample\", inputs = [\"fraud_input\"], keys = [\"fraud_detection_model\"], args = [\"20\", \"2\", \"0\"], outputs=[\"fraud_explanations\"])\n",
     "\n",
     "rai_expl = rai.tensorget(\"fraud_explanations\")\n",
     "\n",
@@ -541,16 +541,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<redisai.dag.Dag at 0x7f8a941a52e0>"
+       "<redisai.dag.Dag at 0x7f80118a6640>"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -573,7 +573,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -634,6 +634,29 @@
     "\n",
     "print(\"Winning feature: %d\" % winning_feature_redisai_dag)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([ 0.  , -0.05,  0.  ,  0.05,  0.2 ,  0.  ,  0.  ,  0.  ,  0.05,\n",
+       "        0.  ,  0.  ,  0.  ,  0.3 ,  0.  ,  0.4 ,  0.  ,  0.  , -0.05,\n",
+       "        0.  ,  0.05,  0.  ,  0.05,  0.  , -0.05,  0.05,  0.  ,  0.  ,\n",
+       "        0.  ,  0.  ,  0.  ])"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dag_expl[1]"
+   ]
   }
  ],
  "metadata": {

…/shapley_explainability/torch_shapely.py …/shapley_explainability/torch_shapley.pynotebooks/shapley_explainability/torch_shapely.py renamed to notebooks/shapley_explainability/torch_shapley.py notebooks/shapley_explainability/torch_shapely.py renamed to notebooks/shapley_explainability/torch_shapley.py

@@ -45,7 +45,7 @@ def index_with_target(x, target:int):
 
 # binary classification - no need for target (output size is 1)
 # multiple output (output vector - target specifies the output index to explain.
-def shapely_sample(tensors: List[Tensor], keys: List[str], args: List[str]):
+def shapley_sample(tensors: List[Tensor], keys: List[str], args: List[str]):
     model_key = keys[0]
     x = tensors[0]
     n_samples = int(args[0])