Merge pull request #7 from lukassykora/small-fixes

Small fixes
lukassykora · Jul 19, 2024 · f38367b · f38367b
2 parents e9b2b1c + 38a500c
commit f38367b
Show file tree

Hide file tree

Showing 4 changed files with 242 additions and 76 deletions.
diff --git a/README.md b/README.md
@@ -48,21 +48,32 @@ min_desired_confidence = 0.5  # min 0.5
 undesired_state = '0'
 desired_state = '1'
 # Action Rules Mining
-action_rules = ActionRules(min_stable_attributes, min_flexible_attributes, min_undesired_support,
-                           min_undesired_confidence, min_desired_support, min_desired_confidence, verbose=False)
+action_rules = ActionRules(
+    min_stable_attributes=min_stable_attributes,
+    min_flexible_attributes=min_flexible_attributes,
+    min_undesired_support=min_undesired_support,
+    min_undesired_confidence=min_undesired_confidence,
+    min_desired_support=min_desired_support,
+    min_desired_confidence=min_desired_confidence,
+    verbose=True
+)
 # Fit
 action_rules.fit(
-    data,
-    stable_attributes,
-    flexible_attributes,
-    target,
-    undesired_state,
-    desired_state,
+    data=data,  # cuDF or Pandas Dataframe
+    stable_attributes=stable_attributes,
+    flexible_attributes=flexible_attributes,
+    target=target,
+    target_undesired_state=undesired_state,
+    target_desired_state=desired_state,
+    use_sparse_matrix=True,  # needs SciPy or Cupyx (if use_gpu is True) installed
+    use_gpu=False,  # needs Cupy installed
 )
 # Print rules
+# Example: [(Age: O) ∧ (Sex: M) ∧ (Embarked: S → C)] ⇒ [Survived: 0 → 1], support of undesired part: 1, confidence of undesired part: 1.0, support of desired part: 1, confidence of desired part: 1.0, uplift: 1.0
 for action_rule in action_rules.get_rules().get_ar_notation():
     print(action_rule)
 # Print rules (pretty notation)
+# Example: If attribute 'Age' is 'O', attribute 'Sex' is 'M', attribute 'Embarked' value 'S' is changed to 'C', then 'Survived' value '0' is changed to '1 with uplift: 1.0.
 for action_rule in action_rules.get_rules().get_pretty_ar_notation():
     print(action_rule)
 # JSON export

diff --git a/notebooks/Example.ipynb b/notebooks/Example.ipynb
@@ -84,7 +84,15 @@
     "undesired_state = '0'\n",
     "desired_state = '1'\n",
     "# Action Rules Mining\n",
-    "action_rules = ActionRules(min_stable_attributes, min_flexible_attributes, min_undesired_support, min_undesired_confidence, min_desired_support,min_desired_confidence, verbose=False)"
+    "action_rules = ActionRules(\n",
+    "    min_stable_attributes=min_stable_attributes,\n",
+    "    min_flexible_attributes=min_flexible_attributes,\n",
+    "    min_undesired_support=min_undesired_support,\n",
+    "    min_undesired_confidence=min_undesired_confidence,\n",
+    "    min_desired_support=min_desired_support,\n",
+    "    min_desired_confidence=min_desired_confidence,\n",
+    "    verbose=True\n",
+    ")"
    ]
   },
   {
@@ -110,34 +118,11 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
+     "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Fri Jul 12 19:43:29 2024       \n",
-      "+-----------------------------------------------------------------------------------------+\n",
-      "| NVIDIA-SMI 555.42.06              Driver Version: 555.42.06      CUDA Version: 12.5     |\n",
-      "|-----------------------------------------+------------------------+----------------------+\n",
-      "| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |\n",
-      "| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |\n",
-      "|                                         |                        |               MIG M. |\n",
-      "|=========================================+========================+======================|\n",
-      "|   0  Quadro M4000                   Off |   00000000:52:00.0  On |                  N/A |\n",
-      "| 55%   62C    P5             26W /  120W |     693MiB /   8192MiB |     11%      Default |\n",
-      "|                                         |                        |                  N/A |\n",
-      "+-----------------------------------------+------------------------+----------------------+\n",
-      "                                                                                         \n",
-      "+-----------------------------------------------------------------------------------------+\n",
-      "| Processes:                                                                              |\n",
-      "|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |\n",
-      "|        ID   ID                                                               Usage      |\n",
-      "|=========================================================================================|\n",
-      "|    0   N/A  N/A      3414      G   /usr/lib/xorg/Xorg                            260MiB |\n",
-      "|    0   N/A  N/A      3565      G   /usr/bin/gnome-shell                          196MiB |\n",
-      "|    0   N/A  N/A      4575      G   ...ures=SpareRendererForSitePerProcess         12MiB |\n",
-      "|    0   N/A  N/A      5120      G   ...seed-version=20240711-180158.427000        204MiB |\n",
-      "|    0   N/A  N/A     11434      G   ...erProcess --variations-seed-version          3MiB |\n",
-      "|    0   N/A  N/A     11826      G   /home/lukas/anaconda3/bin/python                2MiB |\n",
-      "+-----------------------------------------------------------------------------------------+\n"
+      "'nvidia-smi' is not recognized as an internal or external command,\n",
+      "operable program or batch file.\n"
      ]
     }
    ],
@@ -167,16 +152,208 @@
    "execution_count": 5,
    "id": "2947b116-81fb-4c57-9e04-bbfcc25e36cf",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Maximum number of nodes to check for support:\n",
+      "_____________________________________________\n",
+      "80\n",
+      "\n",
+      "SUPPORT for: (0,)\n",
+      "_________________________________________________\n",
+      "- extended by stable attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (1,)\n",
+      "_________________________________________________\n",
+      "- extended by stable attribute\n",
+      "undesired state support: 2\n",
+      "desired state support: 3\n",
+      "\n",
+      "SUPPORT for: (0, 2)\n",
+      "_________________________________________________\n",
+      "- extended by stable attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (0, 3)\n",
+      "_________________________________________________\n",
+      "- extended by stable attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (1, 2)\n",
+      "_________________________________________________\n",
+      "- extended by stable attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 2\n",
+      "\n",
+      "SUPPORT for: (1, 3)\n",
+      "_________________________________________________\n",
+      "- extended by stable attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (0, 3, 4)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (0, 3, 5)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (0, 3, 6)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (0, 3, 7)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (1, 2, 4)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (1, 2, 5)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (1, 2, 6)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 2\n",
+      "\n",
+      "SUPPORT for: (1, 2, 7)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (1, 3, 4)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (1, 3, 5)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (1, 3, 6)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (1, 3, 7)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (0, 3, 4, 6)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (0, 3, 4, 7)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (0, 3, 5, 6)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (0, 3, 5, 7)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (1, 2, 4, 6)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (1, 2, 4, 7)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (1, 2, 5, 6)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (1, 2, 5, 7)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (1, 3, 4, 6)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (1, 3, 4, 7)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 1\n",
+      "desired state support: 0\n",
+      "\n",
+      "SUPPORT for: (1, 3, 5, 6)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 1\n",
+      "\n",
+      "SUPPORT for: (1, 3, 5, 7)\n",
+      "_________________________________________________\n",
+      "- extended by flexible attribute\n",
+      "undesired state support: 0\n",
+      "desired state support: 0\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "action_rules.fit(\n",
-    "    data, \n",
-    "    stable_attributes, \n",
-    "    flexible_attributes, \n",
-    "    target, \n",
-    "    undesired_state,\n",
-    "    desired_state, \n",
-    "    True,\n",
+    "    data=data,\n",
+    "    stable_attributes=stable_attributes,\n",
+    "    flexible_attributes=flexible_attributes,\n",
+    "    target=target,\n",
+    "    target_undesired_state=undesired_state,\n",
+    "    target_desired_state=desired_state,\n",
+    "    use_sparse_matrix=True,\n",
+    "    use_gpu=False,\n",
     ")"
    ]
   },
@@ -433,13 +610,13 @@
     "--min_undesired_confidence 0.5 \\\n",
     "--min_desired_support 1 \\\n",
     "--min_desired_confidence 0.5 \\\n",
-    "--csv_path 'data.csv' \\\n",
-    "--stable_attributes 'Sex, Age' \\\n",
-    "--flexible_attributes 'Class, Embarked' \\\n",
-    "--target 'Survived' \\\n",
-    "--undesired_state '0' \\\n",
-    "--desired_state '1' \\\n",
-    "--output_json_path 'output.json' \\\n",
+    "--csv_path \"data.csv\" \\\n",
+    "--stable_attributes \"Sex, Age\" \\\n",
+    "--flexible_attributes \"Class, Embarked\" \\\n",
+    "--target \"Survived\" \\\n",
+    "--undesired_state \"0\" \\\n",
+    "--desired_state \"1\" \\\n",
+    "--output_json_path \"output.json\" \\\n",
     "--use_gpu 0"
    ]
   },
@@ -483,30 +660,6 @@
     "for action_rule in output.get_ar_notation():\n",
     "    print(action_rule)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "6330b4ed-ae6b-4226-8abc-f9c95ec986e5",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5c4e05e0-3457-4de2-92b2-dbaba606ad05",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "62aa619c-c542-4af6-bd5d-2e9d9efa8801",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -525,7 +678,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.3"
+   "version": "3.10.14"
   }
  },
  "nbformat": 4,

diff --git a/src/action_rules/action_rules.py b/src/action_rules/action_rules.py
@@ -268,7 +268,6 @@ def df_to_array(
                 from scipy.sparse import csr_matrix
 
                 data = csr_matrix(df.values, dtype=self.np.uint8).T  # type: ignore
-                data.eliminate_zeros()
             else:
                 data = df.to_numpy(dtype=self.np.uint8).T  # type: ignore
         return data, columns
@@ -362,6 +361,7 @@ def fit(
             print('Maximum number of nodes to check for support:')
             print('_____________________________________________')
             print(self.count_max_nodes(stable_items_binding, flexible_items_binding))
+            print('')
         stop_list = self.get_stop_list(stable_items_binding, flexible_items_binding)
         frames = self.get_split_tables(data, target_items_binding, target, use_gpu, use_sparse_matrix)
         undesired_state = columns.index(target + '_<item_target>_' + str(target_undesired_state))