Remove normalization

As every dataset is already standardized

gen_csv.py

@@ -0,0 +1,11 @@
+import pandas as pd
+from experimentation.Sets import Datasets
+
+dt = Datasets(normalize=False, standardize=False, set_of_files="tanveer")
+for data in dt:
+    name = data[0]
+    X, y = dt.load(name)
+    z = pd.DataFrame(X)
+    z[X.shape[1]] = y
+    print(name, z.shape)
+    z.to_csv(f"test/{name}.csv", header=False, index=False)

oc1datasets.py

@@ -2,7 +2,7 @@ import os
 import pandas as pd
 from experimentation.Sets import Datasets
 
-dt = Datasets(normalize=True, set_of_files="tanveer")
+dt = Datasets(normalize=False, set_of_files="tanveer")
 print("Generating: ", end="")
 for data in dt:
     name = data[0]

scripts/experiment.pbs

@@ -17,4 +17,4 @@
 
 ### Ejecutable con sus parametros
 cd <folder>
-python experiment.py -H galgo -e <experiment> -m <model> -d <data> -S tanveer -k <kernel> -n 1 -t 12
+python experiment.py -H galgo -e <experiment> -m <model> -d <data> -S tanveer -k <kernel> -t 12

scripts/experiment.slurm

@@ -9,4 +9,4 @@
 
 # LOAD MODULES, INSERT CODE, AND RUN YOUR PROGRAMS HERE
 cd <folder>
-python experiment.py -H galgo -e <experiment> -m <model> -d <data> -S tanveer -k <kernel> -n 1 -t 4
+python experiment.py -H galgo -e <experiment> -m <model> -d <data> -S tanveer -k <kernel> -t 4

stats_stree.py

@@ -25,7 +25,7 @@ def compute_depth(node, depth):
     )
 
 
-dt = Datasets(True, False, "tanveer")
+dt = Datasets(False, False, "tanveer")
 for dataset in dt:
     dataset_name = dataset[0]
     X, y = dt.load(dataset_name)

test.ipynb

@@ -797,7 +797,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.2"
+   "version": "3.9.5"
   }
  },
  "nbformat": 4,

test_validation.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "datasets = Datasets(normalize=True, standardize=False, set_of_files=\"tanveer\")\n",
+    "datasets = Datasets(normalize=False, standardize=False, set_of_files=\"tanveer\")\n",
     "X, y = datasets.load(dataset_name)"
    ]
   },
@@ -821,6 +821,60 @@
     "generate_subspaces(200, 10)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "dd = pd.read_csv(\"data/csv/balloons.csv\", header=None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = dd.values[:,:-1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[1., 0., 1., 1.],\n",
+       "       [1., 0., 1., 0.],\n",
+       "       [1., 0., 0., 1.],\n",
+       "       [1., 0., 0., 0.],\n",
+       "       [1., 1., 1., 1.],\n",
+       "       [1., 1., 1., 0.],\n",
+       "       [1., 1., 0., 1.],\n",
+       "       [1., 1., 0., 0.],\n",
+       "       [0., 0., 1., 1.],\n",
+       "       [0., 0., 1., 0.],\n",
+       "       [0., 0., 0., 1.],\n",
+       "       [0., 0., 0., 0.],\n",
+       "       [0., 1., 1., 1.],\n",
+       "       [0., 1., 1., 0.],\n",
+       "       [0., 1., 0., 1.],\n",
+       "       [0., 1., 0., 0.]])"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -845,9 +899,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.2"
+   "version": "3.9.5"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}