tpot

walidaun · Jan 30, 2017 · 22bdc81 · 22bdc81
1 parent b35e87b
commit 22bdc81
Show file tree

Hide file tree

Showing 4 changed files with 58 additions and 69 deletions.
diff --git a/CarlosFuerte/ML_Submission.ipynb b/CarlosFuerte/ML_Submission.ipynb
@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "metadata": {
     "collapsed": false
    },
@@ -159,7 +159,7 @@
        "max      84.400000     8.094000     2.000000     1.000000  "
       ]
      },
-     "execution_count": 3,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -193,7 +193,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "metadata": {
     "collapsed": false
    },
@@ -242,15 +242,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "ImportError",
+     "evalue": "cannot import name '_safe_split'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mImportError\u001b[0m                               Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-3-528f8f7500fb>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mpreprocessing\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodel_selection\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtrain_test_split\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtpot\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mTPOTClassifier\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpipeline\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmake_pipeline\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmake_union\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mensemble\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mExtraTreesClassifier\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mVotingClassifier\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/dgt377/anaconda/lib/python3.5/site-packages/sklearn/model_selection/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     15\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_split\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mcheck_cv\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     16\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 17\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_validation\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mcross_val_score\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     18\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_validation\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mcross_val_predict\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     19\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0m_validation\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mlearning_curve\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/dgt377/anaconda/lib/python3.5/site-packages/sklearn/model_selection/_validation.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     24\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfixes\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mastype\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     25\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalidation\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0m_is_arraylike\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_num_samples\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 26\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetaestimators\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0m_safe_split\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     27\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexternals\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoblib\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mParallel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdelayed\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogger\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     28\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetrics\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscorer\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mcheck_scoring\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mImportError\u001b[0m: cannot import name '_safe_split'"
+     ]
+    }
+   ],
    "source": [
     "from sklearn import preprocessing\n",
     "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.multiclass import OneVsOneClassifier, OneVsRestClassifier\n",
+    "from tpot import TPOTClassifier \n",
+    "from sklearn.pipeline import make_pipeline, make_union\n",
+    "from sklearn.ensemble import ExtraTreesClassifier, VotingClassifier\n",
     "\n",
     "scaler = preprocessing.StandardScaler().fit(feature_vectors)\n",
     "scaled_features = scaler.transform(feature_vectors)\n",
@@ -268,47 +284,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "     Pred    SS  CSiS  FSiS  SiSh    MS    WS     D    PS    BS Total\n",
-      "     True\n",
-      "       SS    44     9     1                                        54\n",
-      "     CSiS     1   178    23     1           1           1         205\n",
-      "     FSiS     3    26   119           1                 3         152\n",
-      "     SiSh                      40     1     8           3          52\n",
-      "       MS                 1     4    36     9     1     3          54\n",
-      "       WS     1           1     7    13    75     1    13     1   112\n",
-      "        D                 1                 1    22     3     2    29\n",
-      "       PS           1     3     5     4    12     2   102     2   131\n",
-      "       BS                                                    41    41\n",
-      "Facies classification accuracy (NN) = 0.791566\n",
-      "Facies classification accuracy (OneVsRest) = 0.801205\n",
-      "Adjacent facies classification accuracy (NN) = 0.936145\n",
-      "Adjacent facies classification accuracy (OneVsRest) = 0.948193\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "from sklearn.neural_network import MLPClassifier\n",
-    "\n",
-    "sizes = (200,100,100)\n",
-    "clfNN = MLPClassifier(solver='lbfgs', alpha=.015,\n",
-    "                    hidden_layer_sizes=sizes, random_state=15)\n",
-    "clfOne = OneVsRestClassifier(MLPClassifier(solver='lbfgs', alpha=.015,\n",
-    "                    hidden_layer_sizes=sizes, random_state=15), n_jobs = -1)\n",
+    "# Use extra trees\n",
+    "clfExtra = make_pipeline(\n",
+    "    ExtraTreesClassifier(criterion=\"gini\", max_features=0.53, n_estimators=500))\n",
+    "clfExtra.fit(X_train, y_train)\n",
     "\n",
-    "clfNN.fit(X_train,y_train)\n",
-    "clfOne.fit(X_train,y_train)\n",
-    "\n",
-    "predicted_NN     = clfNN.predict(X_test)\n",
-    "predicted_One    = clfOne.predict(X_test)\n",
+    "predicted = clfExtra.predict(X_test)\n",
     "\n",
     "from sklearn.metrics import confusion_matrix\n",
     "from classification_utilities import display_cm, display_adj_cm\n",
@@ -353,34 +340,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "OneVsRestClassifier(estimator=MLPClassifier(activation='relu', alpha=0.015, batch_size='auto', beta_1=0.9,\n",
-       "       beta_2=0.999, early_stopping=False, epsilon=1e-08,\n",
-       "       hidden_layer_sizes=(200, 100, 100), learning_rate='constant',\n",
-       "       learning_rate_init=0.001, max_iter=200, momentum=0.9,\n",
-       "       nesterovs_momentum=True, power_t=0.5, random_state=1, shuffle=True,\n",
-       "       solver='lbfgs', tol=0.0001, validation_fraction=0.1, verbose=False,\n",
-       "       warm_start=False),\n",
-       "          n_jobs=-1)"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "clf_final = OneVsRestClassifier(MLPClassifier(solver='lbfgs', alpha=.015,\n",
-    "                    hidden_layer_sizes=sizes, random_state=1),n_jobs = -1)\n",
-    "\n",
-    "clf_final.fit(scaled_features,correct_facies_labels)"
+    "# Retrain on all data\n",
+    "clfExtra.fit(scaled_features, correct_facies_labels)"
    ]
   },
   {
@@ -400,7 +367,11 @@
    "source": [
     "# Normalize data\n",
     "scaled_validation = scaler.transform(validation)\n",
-    "validation_output = clf_final.predict(scaled_validation)"
+    "validation_output = clfExtra.predict(scaled_validation)\n",
+    "\n",
+    "from scipy.signal import medfilt\n",
+    "# Smooth data\n",
+    "validation_output = medfilt(validation_output,kernel_size = 3)"
    ]
   },
   {
@@ -488,7 +459,7 @@
    },
    "outputs": [],
    "source": [
-    "validationFull.to_csv('TangDarnell.csv')"
+    "validationFull.to_csv('TangDarnell_sub3.csv')"
    ]
   }
  ],

diff --git a/CarlosFuerte/ML_Submission.py b/CarlosFuerte/ML_Submission.py
@@ -1,4 +1,3 @@
-
 # coding: utf-8
 
 # # Machine Learning Contest

diff --git a/CarlosFuerte/tpot_mnist_pipeline.py b/CarlosFuerte/tpot_mnist_pipeline.py
@@ -0,0 +1,19 @@
+import numpy as np
+
+from sklearn.ensemble import ExtraTreesClassifier, VotingClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.pipeline import make_pipeline, make_union
+from sklearn.preprocessing import FunctionTransformer
+
+# NOTE: Make sure that the class is labeled 'class' in the data file
+tpot_data = np.recfromcsv('PATH/TO/DATA/FILE', delimiter='COLUMN_SEPARATOR', dtype=np.float64)
+features = np.delete(tpot_data.view(np.float64).reshape(tpot_data.size, -1), tpot_data.dtype.names.index('class'), axis=1)
+training_features, testing_features, training_classes, testing_classes = \
+    train_test_split(features, tpot_data['class'], random_state=42)
+
+exported_pipeline = make_pipeline(
+    ExtraTreesClassifier(criterion="gini", max_features=0.53, n_estimators=500)
+)
+
+exported_pipeline.fit(training_features, training_classes)
+results = exported_pipeline.predict(testing_features)
diff --git a/CarlosFuerte/y_pred_Matt.npy b/CarlosFuerte/y_pred_Matt.npy
Original file line number	Diff line number	Diff line change
		@@ -1,4 +1,3 @@

		# coding: utf-8

		# # Machine Learning Contest
Expand Down