diff --git a/ravigorasiya65@gmail.com/F1_score_for_iris_flower_datasets_-2019-08-24-10-01.pdf b/ravigorasiya65@gmail.com/F1_score_for_iris_flower_datasets_-2019-08-24-10-01.pdf
new file mode 100644
index 000000000..1b13a64e1
Binary files /dev/null and b/ravigorasiya65@gmail.com/F1_score_for_iris_flower_datasets_-2019-08-24-10-01.pdf differ
diff --git a/ravigorasiya65@gmail.com/iris-f1score.ipynb b/ravigorasiya65@gmail.com/iris-f1score.ipynb
new file mode 100644
index 000000000..b9d71e848
--- /dev/null
+++ b/ravigorasiya65@gmail.com/iris-f1score.ipynb
@@ -0,0 +1,579 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#import all module \n",
+    "\n",
+    "\n",
+    "import keras\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense\n",
+    "from keras.optimizers import Adam\n",
+    "from keras.utils.vis_utils import model_to_dot\n",
+    "from keras.utils import plot_model\n",
+    "import seaborn as sns\n",
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#load datasets iris.150 x 5\n",
+    "\n",
+    "dataset = sns.load_dataset(\"iris\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/gorasiyarahulrameshbhai/anaconda3/lib/python3.7/site-packages/scipy/stats/stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.\n",
+      "  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<seaborn.axisgrid.PairGrid at 0x1a32416048>"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 806.85x720 with 20 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#present all combinational graph that we classify\n",
+    "\n",
+    "sns.set(style=\"ticks\")\n",
+    "sns.set_palette(\"husl\")\n",
+    "sns.pairplot(dataset.iloc[:,0:6], hue=\"species\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Splitting the data into training and test\n",
+    "\n",
+    "X = dataset.iloc[:,0:4].values\n",
+    "y = dataset.iloc[:,4].values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#using labelencoder encod label setosa,verginica or ..\n",
+    "\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "encoder =  LabelEncoder()\n",
+    "y1 = encoder.fit_transform(y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#set binary value of this label\n",
+    "\n",
+    "Y = pd.get_dummies(y1).values\n",
+    "\n",
+    "#split data into test and train sets.by 80%=train set or 20%=test sets\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "X_train,X_test, y_train,y_test = train_test_split(X,Y,test_size=0.2,random_state=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From /Users/gorasiyarahulrameshbhai/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\n",
+      "Instructions for updating:\n",
+      "Colocations handled automatically by placer.\n",
+      "_________________________________________________________________\n",
+      "Layer (type)                 Output Shape              Param #   \n",
+      "=================================================================\n",
+      "dense_1 (Dense)              (None, 4)                 20        \n",
+      "_________________________________________________________________\n",
+      "dense_2 (Dense)              (None, 3)                 15        \n",
+      "=================================================================\n",
+      "Total params: 35\n",
+      "Trainable params: 35\n",
+      "Non-trainable params: 0\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "#create sequential model\n",
+    "\n",
+    "model = Sequential()\n",
+    "\n",
+    "#add weight of hidden layer \n",
+    "model.add(Dense(4,input_shape=(4,),activation='relu'))\n",
+    "\n",
+    "#add weight of output layer\n",
+    "\n",
+    "model.add(Dense(3,activation='softmax'))\n",
+    "\n",
+    "#set learning rate \n",
+    "model.compile(Adam(lr=0.04),'categorical_crossentropy',metrics=['accuracy'])\n",
+    "\n",
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From /Users/gorasiyarahulrameshbhai/anaconda3/lib/python3.7/site-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
+      "Instructions for updating:\n",
+      "Use tf.cast instead.\n",
+      "Epoch 1/100\n",
+      "120/120 [==============================] - 0s 3ms/step - loss: 2.0960 - acc: 0.3250\n",
+      "Epoch 2/100\n",
+      "120/120 [==============================] - 0s 97us/step - loss: 1.1284 - acc: 0.4167\n",
+      "Epoch 3/100\n",
+      "120/120 [==============================] - 0s 79us/step - loss: 0.8432 - acc: 0.7250\n",
+      "Epoch 4/100\n",
+      "120/120 [==============================] - 0s 84us/step - loss: 0.7186 - acc: 0.7167\n",
+      "Epoch 5/100\n",
+      "120/120 [==============================] - 0s 113us/step - loss: 0.6477 - acc: 0.6917\n",
+      "Epoch 6/100\n",
+      "120/120 [==============================] - 0s 93us/step - loss: 0.6074 - acc: 0.6917\n",
+      "Epoch 7/100\n",
+      "120/120 [==============================] - 0s 96us/step - loss: 0.5820 - acc: 0.6917\n",
+      "Epoch 8/100\n",
+      "120/120 [==============================] - 0s 90us/step - loss: 0.5630 - acc: 0.6917\n",
+      "Epoch 9/100\n",
+      "120/120 [==============================] - 0s 102us/step - loss: 0.5490 - acc: 0.7000\n",
+      "Epoch 10/100\n",
+      "120/120 [==============================] - 0s 88us/step - loss: 0.5367 - acc: 0.7083\n",
+      "Epoch 11/100\n",
+      "120/120 [==============================] - 0s 107us/step - loss: 0.5270 - acc: 0.7083\n",
+      "Epoch 12/100\n",
+      "120/120 [==============================] - 0s 93us/step - loss: 0.5191 - acc: 0.7167\n",
+      "Epoch 13/100\n",
+      "120/120 [==============================] - 0s 86us/step - loss: 0.5109 - acc: 0.7333\n",
+      "Epoch 14/100\n",
+      "120/120 [==============================] - 0s 104us/step - loss: 0.5011 - acc: 0.8333\n",
+      "Epoch 15/100\n",
+      "120/120 [==============================] - 0s 83us/step - loss: 0.4878 - acc: 0.8833\n",
+      "Epoch 16/100\n",
+      "120/120 [==============================] - 0s 65us/step - loss: 0.4672 - acc: 0.9167\n",
+      "Epoch 17/100\n",
+      "120/120 [==============================] - 0s 68us/step - loss: 0.4459 - acc: 0.9167\n",
+      "Epoch 18/100\n",
+      "120/120 [==============================] - 0s 88us/step - loss: 0.4152 - acc: 0.9333\n",
+      "Epoch 19/100\n",
+      "120/120 [==============================] - 0s 64us/step - loss: 0.3902 - acc: 0.9417\n",
+      "Epoch 20/100\n",
+      "120/120 [==============================] - 0s 71us/step - loss: 0.3676 - acc: 0.9333\n",
+      "Epoch 21/100\n",
+      "120/120 [==============================] - 0s 66us/step - loss: 0.3517 - acc: 0.9417\n",
+      "Epoch 22/100\n",
+      "120/120 [==============================] - 0s 124us/step - loss: 0.3279 - acc: 0.9500\n",
+      "Epoch 23/100\n",
+      "120/120 [==============================] - 0s 82us/step - loss: 0.3234 - acc: 0.9417\n",
+      "Epoch 24/100\n",
+      "120/120 [==============================] - 0s 105us/step - loss: 0.3398 - acc: 0.8917\n",
+      "Epoch 25/100\n",
+      "120/120 [==============================] - 0s 103us/step - loss: 0.3217 - acc: 0.9250\n",
+      "Epoch 26/100\n",
+      "120/120 [==============================] - 0s 95us/step - loss: 0.3118 - acc: 0.9167\n",
+      "Epoch 27/100\n",
+      "120/120 [==============================] - 0s 84us/step - loss: 0.2802 - acc: 0.9417\n",
+      "Epoch 28/100\n",
+      "120/120 [==============================] - 0s 100us/step - loss: 0.2557 - acc: 0.9500\n",
+      "Epoch 29/100\n",
+      "120/120 [==============================] - 0s 106us/step - loss: 0.2450 - acc: 0.9500\n",
+      "Epoch 30/100\n",
+      "120/120 [==============================] - 0s 97us/step - loss: 0.2390 - acc: 0.9500\n",
+      "Epoch 31/100\n",
+      "120/120 [==============================] - 0s 79us/step - loss: 0.2286 - acc: 0.9583\n",
+      "Epoch 32/100\n",
+      "120/120 [==============================] - 0s 89us/step - loss: 0.2246 - acc: 0.9583\n",
+      "Epoch 33/100\n",
+      "120/120 [==============================] - 0s 109us/step - loss: 0.2142 - acc: 0.9667\n",
+      "Epoch 34/100\n",
+      "120/120 [==============================] - 0s 104us/step - loss: 0.2080 - acc: 0.9667\n",
+      "Epoch 35/100\n",
+      "120/120 [==============================] - 0s 127us/step - loss: 0.2043 - acc: 0.9750\n",
+      "Epoch 36/100\n",
+      "120/120 [==============================] - 0s 122us/step - loss: 0.2034 - acc: 0.9500\n",
+      "Epoch 37/100\n",
+      "120/120 [==============================] - 0s 107us/step - loss: 0.1927 - acc: 0.9667\n",
+      "Epoch 38/100\n",
+      "120/120 [==============================] - 0s 86us/step - loss: 0.1853 - acc: 0.9667\n",
+      "Epoch 39/100\n",
+      "120/120 [==============================] - 0s 104us/step - loss: 0.1876 - acc: 0.9583\n",
+      "Epoch 40/100\n",
+      "120/120 [==============================] - 0s 109us/step - loss: 0.1845 - acc: 0.9583\n",
+      "Epoch 41/100\n",
+      "120/120 [==============================] - 0s 107us/step - loss: 0.1774 - acc: 0.9750\n",
+      "Epoch 42/100\n",
+      "120/120 [==============================] - 0s 109us/step - loss: 0.1778 - acc: 0.9667\n",
+      "Epoch 43/100\n",
+      "120/120 [==============================] - ETA: 0s - loss: 0.1247 - acc: 1.000 - 0s 103us/step - loss: 0.1676 - acc: 0.9750\n",
+      "Epoch 44/100\n",
+      "120/120 [==============================] - 0s 79us/step - loss: 0.1744 - acc: 0.9583\n",
+      "Epoch 45/100\n",
+      "120/120 [==============================] - 0s 84us/step - loss: 0.1638 - acc: 0.9667\n",
+      "Epoch 46/100\n",
+      "120/120 [==============================] - 0s 81us/step - loss: 0.1787 - acc: 0.9500\n",
+      "Epoch 47/100\n",
+      "120/120 [==============================] - 0s 86us/step - loss: 0.1696 - acc: 0.9500\n",
+      "Epoch 48/100\n",
+      "120/120 [==============================] - 0s 80us/step - loss: 0.1591 - acc: 0.9583\n",
+      "Epoch 49/100\n",
+      "120/120 [==============================] - 0s 78us/step - loss: 0.1569 - acc: 0.9750\n",
+      "Epoch 50/100\n",
+      "120/120 [==============================] - 0s 105us/step - loss: 0.1491 - acc: 0.9750\n",
+      "Epoch 51/100\n",
+      "120/120 [==============================] - 0s 83us/step - loss: 0.1561 - acc: 0.9500\n",
+      "Epoch 52/100\n",
+      "120/120 [==============================] - 0s 85us/step - loss: 0.1536 - acc: 0.9583\n",
+      "Epoch 53/100\n",
+      "120/120 [==============================] - 0s 95us/step - loss: 0.1516 - acc: 0.9750\n",
+      "Epoch 54/100\n",
+      "120/120 [==============================] - 0s 94us/step - loss: 0.1625 - acc: 0.9583\n",
+      "Epoch 55/100\n",
+      "120/120 [==============================] - 0s 77us/step - loss: 0.1560 - acc: 0.9500\n",
+      "Epoch 56/100\n",
+      "120/120 [==============================] - 0s 90us/step - loss: 0.1366 - acc: 0.9750\n",
+      "Epoch 57/100\n",
+      "120/120 [==============================] - 0s 101us/step - loss: 0.1393 - acc: 0.9667\n",
+      "Epoch 58/100\n",
+      "120/120 [==============================] - 0s 85us/step - loss: 0.1306 - acc: 0.9750\n",
+      "Epoch 59/100\n",
+      "120/120 [==============================] - 0s 80us/step - loss: 0.1424 - acc: 0.9667\n",
+      "Epoch 60/100\n",
+      "120/120 [==============================] - 0s 75us/step - loss: 0.1539 - acc: 0.9583\n",
+      "Epoch 61/100\n",
+      "120/120 [==============================] - 0s 85us/step - loss: 0.1437 - acc: 0.9583\n",
+      "Epoch 62/100\n",
+      "120/120 [==============================] - 0s 100us/step - loss: 0.1646 - acc: 0.9417\n",
+      "Epoch 63/100\n",
+      "120/120 [==============================] - 0s 90us/step - loss: 0.1290 - acc: 0.9750\n",
+      "Epoch 64/100\n",
+      "120/120 [==============================] - 0s 99us/step - loss: 0.1349 - acc: 0.9750\n",
+      "Epoch 65/100\n",
+      "120/120 [==============================] - 0s 94us/step - loss: 0.1465 - acc: 0.9667\n",
+      "Epoch 66/100\n",
+      "120/120 [==============================] - 0s 90us/step - loss: 0.1198 - acc: 0.9833\n",
+      "Epoch 67/100\n",
+      "120/120 [==============================] - 0s 288us/step - loss: 0.1433 - acc: 0.9500\n",
+      "Epoch 68/100\n",
+      "120/120 [==============================] - 0s 271us/step - loss: 0.1417 - acc: 0.9667\n",
+      "Epoch 69/100\n",
+      "120/120 [==============================] - 0s 81us/step - loss: 0.1307 - acc: 0.9417\n",
+      "Epoch 70/100\n",
+      "120/120 [==============================] - 0s 89us/step - loss: 0.1258 - acc: 0.9667\n",
+      "Epoch 71/100\n",
+      "120/120 [==============================] - 0s 145us/step - loss: 0.1393 - acc: 0.9417\n",
+      "Epoch 72/100\n",
+      "120/120 [==============================] - 0s 99us/step - loss: 0.1444 - acc: 0.9583\n",
+      "Epoch 73/100\n",
+      "120/120 [==============================] - 0s 96us/step - loss: 0.1419 - acc: 0.9583\n",
+      "Epoch 74/100\n",
+      "120/120 [==============================] - 0s 88us/step - loss: 0.1355 - acc: 0.9583\n",
+      "Epoch 75/100\n",
+      "120/120 [==============================] - 0s 103us/step - loss: 0.1103 - acc: 0.9667\n",
+      "Epoch 76/100\n",
+      "120/120 [==============================] - 0s 99us/step - loss: 0.1202 - acc: 0.9667\n",
+      "Epoch 77/100\n",
+      "120/120 [==============================] - 0s 95us/step - loss: 0.1117 - acc: 0.9667\n",
+      "Epoch 78/100\n",
+      "120/120 [==============================] - 0s 73us/step - loss: 0.1159 - acc: 0.9583\n",
+      "Epoch 79/100\n",
+      "120/120 [==============================] - 0s 102us/step - loss: 0.1095 - acc: 0.9667\n",
+      "Epoch 80/100\n",
+      "120/120 [==============================] - 0s 106us/step - loss: 0.1125 - acc: 0.9667\n",
+      "Epoch 81/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "120/120 [==============================] - 0s 80us/step - loss: 0.1084 - acc: 0.9667\n",
+      "Epoch 82/100\n",
+      "120/120 [==============================] - 0s 90us/step - loss: 0.1224 - acc: 0.9583\n",
+      "Epoch 83/100\n",
+      "120/120 [==============================] - 0s 105us/step - loss: 0.1276 - acc: 0.9583\n",
+      "Epoch 84/100\n",
+      "120/120 [==============================] - 0s 91us/step - loss: 0.1109 - acc: 0.9750\n",
+      "Epoch 85/100\n",
+      "120/120 [==============================] - 0s 93us/step - loss: 0.1124 - acc: 0.9667\n",
+      "Epoch 86/100\n",
+      "120/120 [==============================] - 0s 83us/step - loss: 0.1019 - acc: 0.9750\n",
+      "Epoch 87/100\n",
+      "120/120 [==============================] - 0s 111us/step - loss: 0.1018 - acc: 0.9667\n",
+      "Epoch 88/100\n",
+      "120/120 [==============================] - 0s 81us/step - loss: 0.1104 - acc: 0.9667\n",
+      "Epoch 89/100\n",
+      "120/120 [==============================] - 0s 80us/step - loss: 0.0986 - acc: 0.9833\n",
+      "Epoch 90/100\n",
+      "120/120 [==============================] - 0s 79us/step - loss: 0.0996 - acc: 0.9833\n",
+      "Epoch 91/100\n",
+      "120/120 [==============================] - 0s 98us/step - loss: 0.1183 - acc: 0.9667\n",
+      "Epoch 92/100\n",
+      "120/120 [==============================] - 0s 79us/step - loss: 0.0988 - acc: 0.9667\n",
+      "Epoch 93/100\n",
+      "120/120 [==============================] - 0s 90us/step - loss: 0.1041 - acc: 0.9583\n",
+      "Epoch 94/100\n",
+      "120/120 [==============================] - 0s 91us/step - loss: 0.1162 - acc: 0.9667\n",
+      "Epoch 95/100\n",
+      "120/120 [==============================] - 0s 102us/step - loss: 0.1162 - acc: 0.9583\n",
+      "Epoch 96/100\n",
+      "120/120 [==============================] - 0s 92us/step - loss: 0.0975 - acc: 0.9833\n",
+      "Epoch 97/100\n",
+      "120/120 [==============================] - 0s 97us/step - loss: 0.1270 - acc: 0.9583\n",
+      "Epoch 98/100\n",
+      "120/120 [==============================] - 0s 85us/step - loss: 0.1027 - acc: 0.9750\n",
+      "Epoch 99/100\n",
+      "120/120 [==============================] - 0s 89us/step - loss: 0.0932 - acc: 0.9750\n",
+      "Epoch 100/100\n",
+      "120/120 [==============================] - 0s 85us/step - loss: 0.1110 - acc: 0.9667\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x1a32fde4e0>"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#train model using keras\n",
+    "\n",
+    "model.fit(X_train,y_train,epochs=100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#predict model test set.\n",
+    "\n",
+    "y_pred = model.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[1.0906843e-04, 4.7979180e-02, 9.5191175e-01],\n",
+       "       [4.2734195e-02, 9.5715719e-01, 1.0865722e-04],\n",
+       "       [9.9914348e-01, 8.5645291e-04, 1.2037574e-25],\n",
+       "       [1.0906843e-04, 4.7979180e-02, 9.5191175e-01],\n",
+       "       [9.9281186e-01, 7.1880957e-03, 5.7705194e-21],\n",
+       "       [1.0906843e-04, 4.7979180e-02, 9.5191175e-01],\n",
+       "       [9.9502462e-01, 4.9753389e-03, 8.9064300e-22],\n",
+       "       [3.0134590e-02, 9.6938789e-01, 4.7749464e-04],\n",
+       "       [2.1336159e-02, 9.7665352e-01, 2.0102861e-03],\n",
+       "       [6.2816411e-02, 9.3716311e-01, 2.0487576e-05],\n",
+       "       [1.0906843e-04, 4.7979180e-02, 9.5191175e-01],\n",
+       "       [3.7687127e-02, 9.6212721e-01, 1.8565464e-04],\n",
+       "       [1.7809257e-02, 9.7797990e-01, 4.2107501e-03],\n",
+       "       [1.8176759e-02, 9.7794777e-01, 3.8754733e-03],\n",
+       "       [1.3145480e-02, 9.7281533e-01, 1.4039126e-02],\n",
+       "       [9.9623859e-01, 3.7613984e-03, 2.1558834e-22],\n",
+       "       [1.4348639e-02, 9.7566140e-01, 9.9898754e-03],\n",
+       "       [1.1725954e-02, 9.6666592e-01, 2.1608159e-02],\n",
+       "       [9.8238176e-01, 1.7618248e-02, 5.5923329e-19],\n",
+       "       [9.9799466e-01, 2.0053592e-03, 8.9120054e-24],\n",
+       "       [1.0906843e-04, 4.7979180e-02, 9.5191175e-01],\n",
+       "       [1.0072223e-02, 9.5273817e-01, 3.7189610e-02],\n",
+       "       [9.7823799e-01, 2.1761956e-02, 1.6545039e-18],\n",
+       "       [9.7331345e-01, 2.6686598e-02, 4.7349948e-18],\n",
+       "       [1.5223509e-03, 3.6656144e-01, 6.3191622e-01],\n",
+       "       [9.9714476e-01, 2.8552031e-03, 5.3332822e-23],\n",
+       "       [9.8742956e-01, 1.2570441e-02, 9.9446238e-20],\n",
+       "       [4.4173617e-02, 9.5573199e-01, 9.4288720e-05],\n",
+       "       [6.6340514e-02, 9.3364334e-01, 1.6111237e-05],\n",
+       "       [9.8591298e-01, 1.4087012e-02, 1.7795495e-19]], dtype=float32)"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_pred"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[0, 0, 1],\n",
+       "       [0, 1, 0],\n",
+       "       [1, 0, 0],\n",
+       "       [0, 0, 1],\n",
+       "       [1, 0, 0],\n",
+       "       [0, 0, 1],\n",
+       "       [1, 0, 0],\n",
+       "       [0, 1, 0],\n",
+       "       [0, 1, 0],\n",
+       "       [0, 1, 0],\n",
+       "       [0, 0, 1],\n",
+       "       [0, 1, 0],\n",
+       "       [0, 1, 0],\n",
+       "       [0, 1, 0],\n",
+       "       [0, 1, 0],\n",
+       "       [1, 0, 0],\n",
+       "       [0, 1, 0],\n",
+       "       [0, 1, 0],\n",
+       "       [1, 0, 0],\n",
+       "       [1, 0, 0],\n",
+       "       [0, 0, 1],\n",
+       "       [0, 1, 0],\n",
+       "       [1, 0, 0],\n",
+       "       [1, 0, 0],\n",
+       "       [0, 0, 1],\n",
+       "       [1, 0, 0],\n",
+       "       [1, 0, 0],\n",
+       "       [0, 1, 0],\n",
+       "       [0, 1, 0],\n",
+       "       [1, 0, 0]], dtype=uint8)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#convert into numpy array for sklearn classification report to get f1 score\n",
+    "y_test_class = np.argmax(y_test,axis=1)\n",
+    "y_pred_class = np.argmax(y_pred,axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00        11\n",
+      "           1       1.00      1.00      1.00        13\n",
+      "           2       1.00      1.00      1.00         6\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00        30\n",
+      "   macro avg       1.00      1.00      1.00        30\n",
+      "weighted avg       1.00      1.00      1.00        30\n",
+      "\n",
+      "[[11  0  0]\n",
+      " [ 0 13  0]\n",
+      " [ 0  0  6]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Accuracy of the predicted values\n",
+    "\n",
+    "from sklearn.metrics import classification_report,confusion_matrix\n",
+    "print(classification_report(y_test_class,y_pred_class))\n",
+    "print(confusion_matrix(y_test_class,y_pred_class))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}