Merge branch 'master' of https://git.wmi.amu.edu.pl/s444452/mpsic_projekt_1_bayes_classifier
This commit is contained in:
MatOgr
commit
5a363e62f0
163
projekt.ipynb
163
projekt.ipynb
|
|
@ -142,8 +142,13 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"execution_count": 20,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
|
|
@ -160,8 +165,13 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"execution_count": 21,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class NaiveBayes():\n",
|
||||
|
|
@ -171,6 +181,7 @@
|
|||
" self.className = className\n",
|
||||
" self.attribsNames = attribsNames\n",
|
||||
" self.data = data\n",
|
||||
"\n",
|
||||
" #przygotowanie prawdopodobienstw wartosci danych cech w zaleznosci od klasy\n",
|
||||
" def getDictOfAttribProbs(self):\n",
|
||||
" dictionaries = {}\n",
|
||||
|
|
@ -205,8 +216,9 @@
|
|||
" dic[attribsNames[i]] = attribs[i]\n",
|
||||
" sum = 0.0\n",
|
||||
" for key in dic:\n",
|
||||
" sum = sum + np.log(NaiveBayes.getAttribProbs(self,key, dic[key], X_train, clas, dictProbs))\n",
|
||||
" return sum + np.log(NaiveBayes.classProb(self,clas))\n",
|
||||
" sum = sum + np.log(self.getAttribProbs(key, dic[key], X_train, clas, dictProbs))\n",
|
||||
" return sum + np.log(self.classProb(clas))\n",
|
||||
"\n",
|
||||
" #predykcja dla danych\n",
|
||||
" def predict(self, data, model):\n",
|
||||
" attribNames = data.columns\n",
|
||||
|
|
@ -214,21 +226,25 @@
|
|||
" for i in range(len(data)):\n",
|
||||
" probs = {}\n",
|
||||
" for name in self.classes:\n",
|
||||
" probs[name] = NaiveBayes.getPosteriori(self,list(data.iloc[i]), list(attribNames),name, model)\n",
|
||||
" probs[name] = self.getPosteriori(list(data.iloc[i]), list(attribNames), name, model)\n",
|
||||
" keyMax = max(zip(probs.values(), probs.keys()))[1]\n",
|
||||
" predictions.append(keyMax)\n",
|
||||
" return predictions\n",
|
||||
"\n",
|
||||
" def fitModel(self):\n",
|
||||
" model = NaiveBayes.getDictOfAttribProbs(self)\n",
|
||||
" return model\n",
|
||||
" "
|
||||
" probabilities = self.getDictOfAttribProbs()\n",
|
||||
" return probabilities\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"execution_count": 22,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"features = [\n",
|
||||
|
|
@ -245,8 +261,13 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"execution_count": 23,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
|
|
@ -457,7 +478,7 @@
|
|||
"[5 rows x 23 columns]"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
|
|
@ -640,16 +661,19 @@
|
|||
" },\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"# data = pd.read_csv('mushrooms.csv')\n",
|
||||
"for key in NAMES_DICT.keys():\n",
|
||||
" mushrooms[key] = mushrooms[key].apply(lambda x: NAMES_DICT[key][x])\n",
|
||||
"mushrooms.head()\n",
|
||||
"# .drop(['veil-type'], axis=1)"
|
||||
"mushrooms.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"##### Features' distribution \n",
|
||||
"\n",
|
||||
|
|
@ -658,8 +682,13 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"execution_count": 24,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
|
|
@ -2469,7 +2498,12 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%% md\n"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"##### Korelacja zmiennych\n",
|
||||
"\n",
|
||||
|
|
@ -2478,8 +2512,13 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"execution_count": 25,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
|
|
@ -2523,7 +2562,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 26,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
@ -2564,6 +2603,15 @@
|
|||
" plt.show()\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"training_cols = [\n",
|
||||
" 'odor',\n",
|
||||
" 'spore-print-color',\n",
|
||||
" 'gill-color',\n",
|
||||
" 'ring-type',\n",
|
||||
" 'stalk-surface-above-ring',\n",
|
||||
" 'gill-size',\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"plot_chosen_features(mushrooms,\n",
|
||||
" col='odor',\n",
|
||||
" labels=NAMES_DICT['odor'].values(),\n",
|
||||
|
|
@ -2572,7 +2620,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": 27,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
@ -2597,7 +2645,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 28,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
@ -2622,7 +2670,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 29,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
@ -2647,7 +2695,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 30,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
@ -2672,7 +2720,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
@ -2697,8 +2745,13 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"execution_count": 32,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_train, X_test = train_test_split(mushrooms,\n",
|
||||
|
|
@ -2719,8 +2772,13 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"execution_count": 33,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X_test_data = X_test[columns]\n",
|
||||
|
|
@ -2729,8 +2787,13 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"execution_count": 34,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"bayModel = NaiveBayes(classValue, className, columns, X_train)\n",
|
||||
|
|
@ -2739,8 +2802,13 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"execution_count": 35,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"pycharm": {
|
||||
"name": "#%%\n"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -2750,7 +2818,7 @@
|
|||
"acuracy score = 0.9944903581267218\n",
|
||||
"\n",
|
||||
"accuracy score losowych predykcji\n",
|
||||
"acuracy score = 0.49931129476584024\n"
|
||||
"acuracy score = 0.48829201101928377\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -2766,33 +2834,34 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"execution_count": 36,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Accuracy bez \"odor\"\n",
|
||||
"acuracy score = 0.8657024793388429\n"
|
||||
"accuracy score naiwnego klasyfikatora\n",
|
||||
"acuracy score = 0.8980716253443526\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"without_odor = [\n",
|
||||
"columns_wihtout_odor = [\n",
|
||||
" 'spore-print-color',\n",
|
||||
" 'gill-color',\n",
|
||||
" 'ring-type',\n",
|
||||
" 'stalk-surface-above-ring',\n",
|
||||
" 'gill-size',\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"X_test_data = X_test[without_odor]\n",
|
||||
"X_test_data = X_test[columns_wihtout_odor]\n",
|
||||
"X_test_results = X_test[className]\n",
|
||||
"\n",
|
||||
"bayModel = NaiveBayes(classValue,className,without_odor,X_train)\n",
|
||||
"bayModel = NaiveBayes(classValue, className, columns_wihtout_odor, X_train)\n",
|
||||
"model = bayModel.fitModel()\n",
|
||||
"pred = bayModel.predict(X_test[without_odor],model)\n",
|
||||
"print('Accuracy bez \"odor\"')\n",
|
||||
"pred = bayModel.predict(X_test[columns_wihtout_odor], model)\n",
|
||||
"print('accuracy score naiwnego klasyfikatora')\n",
|
||||
"print(\"acuracy score = \", accuracy_score(list(X_test_results), pred))\n"
|
||||
]
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue