{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Naive Bayes\n\nIt is a classification technique based on Bayes’ Theorem with an assumption of independence among predictors. In simple terms, a Naive Bayes classifier assumes that the presence of a particular feature in a class is unrelated to the presence of any other feature.\n\nLet's dive a little into the maths behind Naive Bayes. \n\nStarting with the **Bayes theorem**\n\n![image.png](attachment:40e3e141-8822-472e-9f0b-5d9ad03085e7.png)\n\nHere X represents the independent variables while y represents the output or dependent variable. The assumption works that all variables are completely independent of each other hence X translates to x1, x2 x3 and so on\n\n![image.png](attachment:45649cac-c917-4319-9a68-9e4daea99c94.png)\n\nSo, the proportionality becomes \n\n![image.png](attachment:dad63e9b-6580-4722-93d4-593f4bad056d.png)\n\nCombining this for all values of x\n\n![image.png](attachment:6c457a6d-0027-448b-8961-3038fc6b6ede.png)\n\nNow the target for the Naive Bayes algorithm is to find the class which has maximum probability for the target. Which refers to finding the maximum value of y. For this argmax operation is used. \n\n![image.png](attachment:dde1e786-3cac-40ef-9d2e-bef1e1db746a.png)\n\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-07-04T02:13:05.099919Z","iopub.execute_input":"2022-07-04T02:13:05.100609Z","iopub.status.idle":"2022-07-04T02:13:05.1051Z","shell.execute_reply.started":"2022-07-04T02:13:05.100567Z","shell.execute_reply":"2022-07-04T02:13:05.10425Z"}},"attachments":{"40e3e141-8822-472e-9f0b-5d9ad03085e7.png":{"image/png":"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"},"45649cac-c917-4319-9a68-9e4daea99c94.png":{"image/png":"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"},"dad63e9b-6580-4722-93d4-593f4bad056d.png":{"image/png":"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"},"6c457a6d-0027-448b-8961-3038fc6b6ede.png":{"image/png":"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"},"dde1e786-3cac-40ef-9d2e-bef1e1db746a.png":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAdkAAABdCAIAAABmc4svAAAACXBIWXMAAA7EAAAOxAGVKw4bAAAgAElEQVR4nO2deVQbV5b/q0orAgRCgBACsYhVIIQMBgLGGDBewBjHOKST2LEbJ+4k42lnZjKnZ9I9PSfdfSbnzEnP9PT0ZJw47qTjOE56YsfGJngH29gYsxNALAIEYkegDUmUVKr6/fF+raODAWNjB9n9Pn+BVPXqlarqW/fdd+99KEVRCAQCgUDWFGytOwCBQCAQqMUQCATiBkAthkAgkLUHajEEAoGsPVCLIRAIZO2BWgyBQCBrD9RiCAQCWXugFkMgEMjaA7UYAoFA1h6oxRAIBLL2QC2GQCCQtQdqMQQCgaw9UIshEAhk7YFaDIFAIGsP1GIIBAJZe6AWQyAQyNoDtRgCgUDWHqjFEAgEsvZALYZAIJC1h77WHYBAIAiCIBRFmc1mtVo9NzcnFosFAsHExMTIyAiGYRKJhMfjoSi61n2EPEGgFkMgboHFYqmurp6amqqvr4+Jidm7d29jY2NXV1dHR8ePfvSj7du30+nwaX2WgT4KCGTtoSiKIAiLxRIZGalWq0+dOtXd3R0YGCiRSNrb2xsbGx0Ox1r3EfJkgW9aCGRJSJLs7++/cuWK1Wp9ckdBUTQzMzM5OXnTpk0IgszNzdlsNh6PFxMTw2QyWSwWRVFP7ugQNwFqMQSyHBRFqVSqS5cujYyMPPbGMQzz9/ffuHHj+vXr6XR6QEBAb2/vwMDA9u3bpVKpw+EYHBzU6/USiYRGoz32o0PcCqjFEMiSYBgWFRX1xhtvxMbG/va3v+3r6wOflJWVMRiMR2tzfn7+22+/7e7uxjBMKBTu27fv+eefj4mJodPpOI53d3fbbLacnBwGg2G1Wtvb261Wa3x8PNTiZx6oxRDIcmAYFhMTExYWNj4+/t577wEtfuedd3x8fB6tQZ1O19HR0d3dTaPR4uLi3nzzzYCAAPAVjuN1dXUeHh7p6ekURZlMpt7eXpFIFBAQMDU1FRAQgGFwgueZBV5aCOTB0On0bdu2gb/BPNtqWiNJEkEQFosllUqdQowgCI7j9fX1PB4vIiKCoii73e5wOAIDA/v7+8+ePYvj+GoOCnFzoBZDIA8Gw7DQ0NDH2CCKosBB7PohRVG+vr5bt25ls9koinK53LS0NB6P19fXx+PxoFH8bAN9FBDIiuBwOI+9TWAgAyiK8vb2Pnz4sEgkAoETXC539+7dcrmcx+MlJSWxWKzH3gGI+wC1GAJ5MCiKPunAMhRFPTw8Nm/e7PyETqdLJBKJRPJEjwtxE+CoBwKBQNYeqMUQCASy9kAthkAgkLUHajHEjbDb7SaTaeUJx3a7Xa/Xw2AvyDMAnLuDPAp6vX52dtZZsIbBYAQHBzOZzEdukCTJ6enprq6uoaGh+Pj4tLS0lZSIHBsbO3/+vEQikcvlAQEBj5wLB1kGiqLm5+eNRiOLxfL19V1lU1ardXp6ms1mCwSCh9oXx/HZ2Vk2m83lcu/PQjSbzaOjo+CeoSiKxWIJBAI2m72a3v7AQC2GPAq1tbVnzpzx8PAIDQ3FMIzL5ZaVlYEau2azube319VWpSiKRqNxudyAgIBF42QdDkdLS0tFRcXMzExMTMzKJZVGoxEE8d1339XU1BQVFaWnp8PAr6Ww2WxqtVqr1br+/iiKcjgcf39/Pp+/6KsUx3GNRtPR0TE7OxsfH//cc8+tpg8Oh6O3t/f48ePx8fFvvPHGQ0VM63S6S5cuoSgqlUqjo6N9fHxc39ZTU1OnT5/GMMxisYyNjQUEBJSXl0dFRa2mtz8wUIshj0JPT8+pU6fy8vJA5QQOh+N8kq1W65UrV27cuOFwOKRSaUhICEEQZrPZaDQKBII9e/ZERkYueAibm5s/+OADs9n8wgsv5OXlCYXClfSBoiihULh3795bt26dPHnyP/7jP/7mb/4mPz8f5kQsCo7jzc3NX331ld1uDwgIkMlkFEVZLBaTyeTl5ZWXl7d+/foFhqTZbG5oaKiqqsJxXCaTeXl5rbIPJEmOj4+fP3/eaDS+8cYbD7Uvk8n08vL6/vvvW1paZDJZQUGBWCx2fsvhcGJiYjAMGx4erqyspChq165dq+ztDwzUYsijAAaJcXFxO3fudH2AKYry9PQUi8U3b960WCyFhYUpKSkkSep0ujNnznz77bc6ne69995z3WV0dPTDDz/s6+v7+c9/XlxczGAwVriABYqiNBqNz+fv2rWLy+X+5je/+e1vfysWi2NjYx/7+T7tgGF7UFBQX1/f8PDwnj17MjIyKIoyGAx1dXUVFRXd3d2//OUv4+PjnbsA7T527Jjdbi8rK9uwYYO/v//qe4JhGIvFegRvkq+v75YtW0JDQ6uqqioqKmZnZ3/84x87uyQQCEpLS0mS7OzsvH79+ujo6FP3Sn7KugtxKxwOx4IMCJCwAJLE2Gz2rl27MjMzs7Ozi4qKCgoKzGbziRMnbDab6y6XLl26cOHCyy+/vG3bNiaT+bArCaEoiqJodnb2/v37W1pazp49Oz8//xjO7dkCRVEmkymRSAIDA729vbdv356VlbVhw4YtW7bs2LHDx8entra2u7vbOQFAkuTIyMif//xnjUZTVlZWWFgYFBS0trXigCssJSWlrKxMIpFUVlbeuHFjwbQtKBXims34FAG1GPL4mZiYIAgiMjIyICAAaCuNRhOJRN7e3hMTE66PytjY2OnTp7lcbmFh4WqSjJlM5qZNmxITE0+dOqVWq1d/Cs8eJElardb5+XkPDw+5XA5eojQaLSAggM/nEwSh1+udl8ZqtTY2NtbU1OTk5GzevJnD4VAU5Q4L7oFcxKKiIhaLdfr06bGxsbXu0WPDXXwUFEVNTk7W1NT09/dHRkbm5eUFBgaCa3/ixImBgQEEQWJjYwsKCvh8/qK7EwSxwixVOp3+wPGLxWJRKpXNzc2Tk5N0Ol0sFotEovHxcYVCERkZyWAwBgYGamtrNRpNQkJCfn4+m81WqVQ3b96cmppKTEzMz8/ncrnO1hwOB/BzjY+PEwQRHR0NltJJSEgAazeoVKpbt26Njo7K5fL8/HwGg9Hb21tTUzMzM5OSkrJp0yYOh6PVaqurq0GZmKKiopCQEFc7xeFwqNXq+vr64eFhHMdFIlFSUtLg4CCfz8/OzgYzWmaz+fr16+3t7d7e3i+//DKfz0dR1GKxXLx4saurKzc3Nz09/bEsqtbU1ITjeFZWlmsPQdUxDofj+ki3tbU1NDTs2LEjKChowaOu0WguXbo0OjqqUCi2b98ORrVms/n8+fM9PT0IgmzYsCEnJ4dOp4PrLhAIMjMz33///ebmZuA6XKaH4Ipcv379xz/+MY/HW/0puz8EQYyMjBgMhqCgIOevDR4cgiAwDPPw8AA/GkmSU1NTYKIsJycHxE44r47D4RgfH6+pqRkZGUlKSsrNzfXw8CBJcnJy8tKlSzqdLi8vTy6XP1THNBrNrVu3NBpNbGzszp07mUwmRVGzs7O3bt1qa2tjs9lJSUl5eXlgiRMmkxkbGyuTyS5cuNDQ0CASiVYTwOM+uIsWT01NXblyZXx8/OLFiziOs9nsLVu2eHp6IghCUdTJkyc1Gk15eXlmZuaiWtzd3X3x4kWtVruSY5WWliYmJi5z/WZmZioqKm7cuMFmswMCAmg02unTp+fm5qxW67/8y7+Eh4e3tLS0t7dbLJaPPvpIKBSKxWKTyfT1119fvnx5aGjoyJEjmZmZTi02m82XL1+uqKhgs9mBgYEYhl2+fFmv109PT//jP/6jRCJpbGzs6OiwWq0ff/yxWCyOjIycmpo6efJkTU2NRqORy+V+fn6hoaEnTpw4d+5cd3c3m822Wq0HDhzw8/MDTwiO47dv3/7yyy9xHJdIJCiK3r17t7Kysr+//5VXXsnIyGCxWARB/PnPfwZBDlevXvX19X3xxRcJgjh37tyHH35YX18vFApTU1MfixbfuHHDbrfn5uY6tdjhcDQ2Nur1+ueee855CIIgOjs7dTpdWlqal5eXq+U1MjJy7do1o9H4xRdfnDt3LiEhQSKRUBQFqvp+/vnng4OD//M//7Nx40bkLzLBZrMTExNZLFZjY2NJSQm4ee7HarUyGAyKotra2v77v/8bhH/Mz88zmcynzsP4UIBC9QaDITc313nz2+12tVrd39/P5/PDwsLAL+BwODQazY0bNxQKhasHGUEQkiQnJiauX7+uUqnq6upqamrEYnF8fPz4+Phnn3128uRJOp0eFha2ci0Gb4i6urr+/v7z5897enpGRESkpKSAb7Va7ddff63X63/605/m5OQgf7nWXC5XKpVWVlbevHkzPz9/UU146nAXLVapVCRJ7tmzh06nf/jhh/fu3UtPTweP0969e7/99tv5+fmMjAw/P79Fdx8fH6+oqBgaGnrgMApF0dTU1AV3mCsmk+ncuXPHjx+XyWQHDhxQKBRMJvMXv/jF0aNHnYPu7u7ugICA7OzsY8eO9fT0tLa2gk9efPHFK1eupKamOoVgfn7+4sWL//Vf/xUdHb13797U1FQmk3n8+PGf//znQUFBIpEIRdGuri6hUJidnf2nP/1JqVR2dHQ0NTXx+fw333zz1KlTra2t3333nbe3d39/f0lJiUKhOHnyZG1t7a5du0AMmcPhaGho+OCDD+x2++HDh0HFxQsXLhw4cMBut0dHRwOLcnx8fHp6urS0ND8//+LFi1999dXOnTvr6uouXLiQm5uL47hcLn8sDkGtVqtSqRAEUSgUGIYRBGG1Wtva2sDb6PXXX3eGnZlMpu7ubgRBQkND6XS689pRFKVWq3EcP3jwYHd39yeffFJTUwNK5Hh5eRUXF58+fdpisdz/5hAKhX5+fs3NzSaTaVEtdjgcFRUVYrE4MTHRw8ODwWDQ6fTBwcG6urq8vLygoKDVn77bguO4UqkkCEIul9PpdJIkzWbz4OBgRUXFxMTEvn37oqOjQQkkHMdVKtXs7GxERERgYKBrIwRBTE1NGQyGF198kc/n/+///m99fX1gYCAwUYuKilAUdQ1veCB2ux24rcrKyubn50+dOnXx4sWUlBQURfl8fk5OzqVLlzo7O1NSUlyjFdlstkQi8ff3VyqVOp0OavHjJDAwMCIiIiAgICkpicPhqNVqMJjCMMxsNuM4HhcXJ5PJlnIpxsbGHj582Gw2r0SL5XL5UtO4JEl+//33n3/+OY/HKy8vVygUYEuRSMRisUJCQkB4rEKhCA4OZjAYJEna7fbW1la5XL5z5046nZ6RkZGcnOzh4YEgCEVRfX19H3/8MYIg5eXlaWlpwCILCQlhMpkCgSAgIIBOp6empgKTZH5+HpiK8fHx27ZtEwgEarW6t7f3/Pnzubm5+/fvT0tLu337dmVlJUmSTteeTqc7evRof3//v/3bv23btg3cskDdwGgOnAKdTi8rKwsJCUFRNCIioqenp6Wl5bvvvpPL5QcPHkxLS3tcC/l0dXXNzc15e3uPjo7qdDqTyTQ8PFxbW0tR1E9+8pOCggKngM7Pz09NTXl4eHh6ei64cCEhIUFBQT4+PpmZmV988cWVK1fKy8vBNkajEQyEo6KiFuzl4+PD4/FGRkaWysQjSbK6uhrH8cLCQuCaGBgY+Oabb9rb25OSkp5hLSZJ0mAwDA0NIQiC43hTUxNYTK+9vb2rq6ukpOTVV18Fhg6IEO/q6mIwGEKhcMGTgmFYUFAQ+PFHR0c5HM69e/f8/Pxu375dVla2ZcsWrVb7UD8jjUYLCQnx9/cXCoVyufzEiRNg0WsajeZwOIxGI0EQMpksLi7O9eZkMBh8Pt/X11ej0UxMTICx4GP6qdYMd9Hi6Oho8IdAIPDx8dFqtTqdzuFwYBj2/fffG43G0tJSsVi81ChSJBKVlpauvhtWq7Wqqmp0dPRv//ZvQdIBGDiPj49TFBUfH8/hcOh0elxcHIIgPT09OI5TFOXn51dUVMTn8zEMKy4udraG4/i1a9c6OzsPHToUFxfn9Gx2d3cDixW0JpVKEQTp6uoyGAwOh8PLy6uwsBAsqAOc4F5eXrt3705PT2cymXa7naKowMBADw8PYMU0NDRcu3YtNzc3KysLONpQFJ2YmHA4HGKxGHhFQCius2NpaWmnTp368ssvBQLB7t27/fz8XLu9Stra2oxGY3x8fENDA41Gs1qtBoNBJBJt3rw5Pz/fNXGLoiiHw8FisRaYtyiKhoeHg7/lcrm3t/e9e/ec3yqVSr1eX1payuVyXd0aKIoyGAwGg7HM8vU0Gq24uLi2tra2tlYkEhkMhrNnz6rV6k2bNj2WgC23BTh5JyYmOBzO+Pj47du3HQ6HTqej0+kvvPDCpk2bYmNjXT3IWq2WTqff70mn0+lCoVAoFJIkKRQKORzO3bt3MQzbsGFDSUmJl5eXszo+SKTs7OyMjIx0Xs37YTKZISEhoIehoaFMJnNyclKv1/P5/Pn5ebVabbPZdu7cucA8R1GUxWJ5eHjYbDadTkeS5DOwHqC7aLETHx+f4ODggYGB6elpoERVVVUhISG5ubmrzL9cCVqt9ubNm76+vnK5HNjgYHartbUVQRCgxc6Nm5ub5+bmIiIitmzZAoR4QWsmk+ny5cuenp7JyclO04+iqLt371IUlZiY6Bpm29jYaLVaIyIicnJyQGtms1mj0ZAkWV5enpKSwmQySZLUaDRWq1UikXh7ewMtPnfuHEEQWVlZ4BPQ2p07d3AcB3shLhMvgISEBJvNNj4+/vrrr0dERACxflyWRVtbm9VqLS4uTktLA08ISHgNCgoCnVlwrOVnXCMjIzkcDph08vX1nZubu3nzZkJCQnZ2No1GW7AvcCgvdSIURWEYVlhYKJVKP/3007NnzxoMhr6+vv3794MZKjcJFXgS2O324eHh8fFxMBUMxm0MBsPf3z8wMHDBW42iKJIkMQxbJgoYwzAvLy8/P7++vj4fH5/S0tIFTiEcx+/du3fs2LHXX399GS12QqPReDyeQCAwm81DQ0N+fn46nU6pVAoEAufk84IOgFf4k64r/YPhdlrs7e0dFRXV2to6PT0NJhaam5t37dp1f7KWK2q1urq62mg0rsRHUVBQEBUVdf8kFUVRY2Njk5OTYWFhQUFBzhuxq6urr6+PwWBIJBJX9WxpaTGbzdu3bweRFfcfa2ZmRqVS8fn84OBg5+GGhoY6OzsZDEZ0dLTrHdbQ0GC1WnNycpx9GxoampqaEovF2dnZ4Lhms1mpVNLp9IiICLAvUHY2mx0fH++ckDEYDNXV1TabLS0t7f4pShzH+/v7CYLgcDixsbHAWn9cGqTT6QYHBymK2rp1a0pKyqKX7KGO5ePjExERoVarBwcHFQrFwMBAU1PToUOHAgICHrbb4NUFwlFIkkxNTR0YGEhPT5+ZmZmYmFi0ysEzg81mGxgYsFgs69evz8nJuV/aHvYGIAhidnZ2bm6OyWTGx8cvOqrgcrnr1q0TiUQrbNPb2zs+Pv7OnTuDg4OJiYkajUatVj/33HOLOqDBe/cReu62uJ0We3l5hYeHOxwOUH/rm2++CQ0N3bhxo2uI2P309fX94Q9/GBgYeOBUOIZhAoEgLCxsUS02mUwOh4PNZjuTDkwm0xdffDE1NZWQkABiKsDGNputq6trfn4+PT190dxQkO5ps9mYTCaLxQKtORyOTz/9dGRkhM/nC4VCZx9sNltHR4fNZktNTQU2C4Igvb29U1NTICQD7D41NdXc3Awm/Zw9MRgMNBrNx8fHee5nzpzp6emhKCo5Ofl+Lb548WJnZ6e/v//09PT8/Lyz8ceCWq2enJz09/cHjunlN8YwjMlkzs/PL8j+WEBGRkZNTY1SqUxMTKyqqhKJRPn5+fdvBkrYgIiIpQ5NkmRFRUVnZ2deXh6Tybx8+fLWrVvr6+srKioOHDjwsNVqnhYoipqbmxsaGmIymdHR0asPlQGvtKtXr6IoimHYokG+LBYrLS3NOb5cCd7e3gkJCdeuXRsYGDAajS0tLSwWa/Pmzc9GyNoDcTstZjAYoOCW0Wi8c+dOW1vb3r17xWLx8kZQeHj4gQMHZmZmVnKI2NjYpSwg8LJ1ppMRBHH+/Pm+vj6Hw5GYmOjl5UWSJEj0mp6eBj7ZmJiYpcpBmc3mBSlAVVVV33//vd1uDw8Pd1XPiYmJyclJiqJiY2Odd55SqTQYDElJSWAlSgRBtFrtwMCAQqEQCASuq/6ANYPBv42NjXfv3rVYLEFBQUKhEMMwZx8wDOvq6vroo49KSkq4XG5HR8fY2Ji/vz/6F+bm5qqrq9vb22NiYgoLCz09PY1G4+effz47OyuVSkHg5/K/bU9Pz+Tk5Pr1651vlGXgcDgikQjUAFvm+kqlUgzDlEqlSqW6cOHCL3/5SyCa929vMBhmZmbWrVu3TIEuPp+/b9++hISEyspKh8MRHBy8Z8+e27dvP8NGscPh0Gq1Q0NDXC43NDT0gWcK0pQdDofZbF7wFXBfWCyW2travr6+559//ne/+11TUxPi4iugKEqj0YCiE7GxsSufyPHw8AgJCcFxvLe3t7+/v6mpqaCgACyJff+1djgcOI6DSYIVtu/muJ0WIwjC5/O5XG5fX19nZ6dcLnc1FZciOjraOfu3GlgsFoZh4+Pj/f39NBqtvr6+paUlPDwcWKMIgiiVSi8vr+DgYJVKBZzFIBbi/qZQFAXT0BMTE729vX5+fk1NTdeuXQMOUGesBaCvr89isURFRTmNZbPZrFKp7Ha7TCYDygKiPq1Wq1gs9vX1vXfvHpfLjYmJYbFYWq22ubkZ+NkrKyslEgmLxQK2v1qtNhqNCIIMDw/7+/t/8skn4PGwWCw3btzo6uqSSqU1NTVxcXGhoaGXL1+emppqbW09e/asSCRKS0tDEKS/v/+jjz76h3/4h6KiouV/PZvN1tTUZDQaQR7KA+1iLy8vqVSKoujAwIDdbl+qxFpMTAydTlcqlX/84x8TExNBnOmiaDQavV6/fv16b2/vRTeg0WigZIzdbsdxnMvlEgQhEAhKSkqW7+pTDUEQQ0NDSqUSTPkuvzGYFgsPD7fZbJOTk65f4Tje0dFx7969mJiYqqqqzMzMrKysr7/+WqVSjY+Pczic3t5ef3//sLAwgiCUSuWZM2cOHDiwci1mMpkBAQEEQbS1tdXW1vr4+OTn5y8lxHNzc0aj0Rmzv/Jfw21xx3MAAS6NjY12u33z5s0/2MgRRdHQ0NCIiIiRkZHf//73v/rVryoqKnJycsRiMYPB0Ov1XV1dTU1Nc3NzFEW1trYaDIYNGzb4+Pgs1Vp4ePi6deu0Wu3Ro0d//etff/rpp2lpaaBQenx8vKvt1tTUZDKZcnJynO6O0dHR4eFhV18zCPwE09yDg4PXr1/X6XQUReXk5FAU9dlnn/3mN785evRoUFBQUlKSj48PjuNqtfrOnTsGg6GxsfHf//3f33vvPYPB8NZbb/F4vOTkZJIk6+rq2tra6urqwEl5enru3LnzrbfeAiG3BEFwudysrKzg4OCioqLljWK73d7U1HTnzh2HwzE2NjY2NvbAsgAYhslksuDg4Js3b+p0uqU2A6mJDQ0NXV1dR44cAbEi929mMpmampqYTGZqauoDC9fSaDS5XH748OHV1x5zc4AQV1dXj4+PWywWtVptt9uX38XT0zMhIYGiqNHRUZPJ5PzcYrFcvXr117/+9fHjx/39/bdv387j8TIyMkBlvs7OztraWhD7FBQUlJGRwefzMzIyVt5VGo3m5+cXGBjY39/f3d39wgsvOHPoF2Cz2cbGxvR6PZjaeTZcxu5oF3M4HF9fXzabXVJSIpVKH0sm2EpAUVQkEu3du9fDw2NychLDsLKysuzsbD8/v9bWVqPRODQ0FBMTA6TZZDJFRUVt3LhxqYd5bGwMx/H9+/cjCDI8PKzRaLZt21ZQUHD8+HGSJIE969zYZDLFxsZu3LjR6VwzmUw8Hm/Lli3O5DoajZaUlLRlyxaTydTS0qJQKBISEhgMxmuvvQac1wMDA5s2bSorK2MwGFu3bh0cHGxsbAwPD5fJZKOjoyB67MiRI+Hh4TQaLTEx8YUXXpicnLx3715WVhYoQ7x161YEQWw2m7+/v0qlAmVWbty4sWPHDplMtrz1odfrq6urGQyGQqGgKOrOnTsSieSBBotUKt28eXNlZaVSqXR1x7vi6+vL4XAcDseBAwdANOH9zx5FUSqVqrq6Oisra926dStxVcfHxy+T8vPMAKKABgcH161b5+np2djYmJ2dvXxyBIPBiIiIiI2NVSqVAwMDziQ6UIc6LCzM19d33759wcHBOI7v2LFjeHgYvAUVCgUImTCbzT09PSwW62F/YTabDeb6MjMz09PTl9oMTGKbzeaMjIzlZ5KeItxOi8FIHMfx4uLi3Nzcxzuz9EBYLFZxcXF0dLRerw8MDIyLi+NwOAqF4siRI1qtViwWA+8wRVFbtmxJTk6WyWSLDvrGxsY+++wzoVC4fft2gUAwPT3t7+8vlUrHxsZGRkZEIlFwcLBTdyiKKiwsTEtLUygUToEWiUSHDh3y8fEBpgEYqcXGxr7zzjvDw8MCgQBsTFGUQqH4+7//++HhYZAYCrJR3nrrraGhIW9vb/AErl+//p/+6Z9CQkJkMhnwr/H5/Lfffrujo4PP569bt871LLy8vGQy2cTExPz8fH9///Dw8C9+8Qunz3op6HR6SkpKYmIiCIteariwAD6fX1ZWdvPmzS+//DIuLm5RG+fevXseHh779u3buXPnolPnoPbjuXPntFrtu+++u8Lyx38lMBiMyMjI/fv3M5lMYLQ+0MGKYVhwcPCOHTuOHz9eV1fnDNHhcDgFBQWJiYlAqREEYbFYqampP/3pT4GJ6kwXMplMHR0dQqHwofI+QN16BEF27dpVUlKy1P3mcDhGR0ebm5sDAgI2bNiwmpJSboV7aTFFUUNDQ1VVVTwer7i4WCQS/cCeIBRFfX19FwysPDw87h9qAV/qUly7diC8icMAAAk6SURBVO3EiRPl5eVsNnv9+vXOz0Hd1fLycl9fX9db7f7lEkABlwUfAtNDoVC4dphOp8tkMplM5rplYmJiYmKi89+oqCjXNQ5ApK1EIgGJxQvw9PSMjY29c+fOwMBAVVXV1q1bwezZMueLIAiPxwNm9cOSmZlZXl7+pz/96bPPPjt06NACk02lUv3nf/7nxo0bX3vtNfDuuf8RNZvNX3/99fnz5/fs2bN58+ZneBbuEfDw8Fi/fr3rTfhAwFOQl5d38+ZN4BeWyWQoirLZbLlc7momoyjq6emZlZXlurvD4ZiZmZmcnHQd5z0QgiB6e3svXLgQFRX1yiuvLFXtgKIonU53+/btoaGh4uLihISEZ8NZjLiJFlsslkuXLiUlJREE8X//939DQ0N79uwBdV7cM/z+gV1qaWmZmpoKDQ11dUQolcqKiorQ0FAQxrDy1h47yx8RTN2cPXv2iy++4HA4hYWFIMfvCXXG29v71VdftVgsV65csVqte/bsEQgEra2t0dHR8/Pzf/jDH2w225EjR0CQ6YJu2Gy24eHhs2fPVlVV5eTkvPnmm868L8hqoNPp8fHxL7300rFjx44fP37kyJGIiIgFP/5St4TNZhsdHbXZbCAwfHZ2dinDhSTJ2dnZ7u5ukKb01Vdf6fX6gwcPgkzURTEajdXV1ZWVlfHx8c8///wKh19PBW6hxRMTE8eOHQNmoFar3b1798aNG729vd1TiFcCyONobW1NT08Xi8UEQXR0dBw7dsxisbz55ptJSUnuHIiDYZhYLNbr9R0dHf/8z/8cHBz8pE0PkUh0+PDhmJiYa9eunTlzJjIy8vPPPw8NDcVxXKvV/uxnP0tJSVnUO6HRaP74xz9OTEwUFxfv3r07NDT0ifbzrwcURblc7tatW+fm5iorK3//+9+XlZUlJiauxDmLYRhYc+vOnTssFisiImKpLUmSHBoa+vjjj+fm5rhcrsViefXVVzMyMhYd2YDMr8uXL9fU1ISHh7/00ksxMTGrOkk3wy20eGxsbHp6uqmpCRTtLyoq4vF4T68QIwhSWFgIyvr87ne/8/X1Bbn5JpPpjTfe2L17t9vO3QN/IoIgJEn6+vpu3749JSVl0dcGhmFsNruhoeH999+n0Wi+vr579+51TjM+AgKB4JVXXpHJZP39/RaLpb6+vr29PScn58iRI1lZWWD+9n43MVirYvfu3VKp9JnxG7oJICvq5ZdfFgqFV69evXDhgsVi2bx58wN3ZDKZycnJP/nJT7RabWRk5AL3CIqiNBrNeZvp9fqmpiatVpubm7t37968vLylYmAmJye/+eab4eHh1NTUkpKSqKgoV8nu7+8/efIkqLysUqmWqpjqzriFFguFwtdeew3HcYVCkZycDKTq6RViBEHCwsLefvvt+vr63t5ei8XCYDDWrVuXnJwMFh9yz1MzGo0nT57cvXu3Uqm8dOlSSUnJnj17lqoBkp6e/u6771osFpAdQ5Lk6ssCYBiWnJycnJw8PT39zjvv8Hi8TZs2SaVS8Mgt+qOFhoYePHhwlceFLAWGYaBuVGJiYk9Pz1JR2wtAUVQgEBw4cOD+r2g0mkQiOXz4sFgsBjl7YWFhhw4dYjAYGRkZzonlRWEwGFFRUTk5OVKp9P7bEtyECIIEBgb+6Ec/EgqFwcHBD3GqbgC6+kcI8mzQ1dW1Y8eOwsLCmZmZsLCwgwcPghoga/7mcJMR0uzsLJ/Pp9PpBQUFJ06ceOSauTqdbt++fd99952Pj8/bb7/9r//6r4+3n5CnlGdkChKyekwmU2hoaGdnZ1xcnPsIMfKUj5AeARzHW1tbQXQX5K8Ht/BRQNyBkJCQn/3sZ56enlKpFCyF99cmgu4AmM56//33i4qKXn311YfdHcfxkZERh8MRHh7+V1JS55kBajHk/yMSiVZe3hDyhKAoymazcTich53gJQhiYmKivr7+xo0bYWFh5eXlUIufLqAWQyAPh8PhWGbpkFWComhYWNi77767YCWL5bHb7Uql8vr165OTk9evX09PTycI4gn1EPKEgFoMgTwYkGYN/rBYLAaD4aG0coWYTKajR4+CBbH27du38h1JkrRarT4+PlFRUU1NTQRBQP/SUwfUYgjkwZAkCRa3pihKr9dPTk4+co1WkiRBrWq73T4yMuL6FUVR09PTR48e3bZtG9Bii8Vy9uxZcOgF0Gi00NBQEK7OYDASEhISEhLAAiUwOOppBMZRQCAPgCAIs9l8+fJlBEEoigKrq1gslgcWBV0ASZI4jnd2dvb39yN/KQesUqmc0dmenp4vvfQSgiDr1q1DXFY2WBSCIJyuErD6HMx2eaqBdjEEshxWq7W1tfX27dunT59GEISiqJmZmZMnT7JYrJSUlKSkpBVOkYE6ws3NzSdOnADV/R0Oh0ql+uCDD0pLSxUKhb+/v91u7+7udtaTApV3HspZAXl6gVoMgSwJWHi7srKyvr7ex8cnOTkZfE4QRFVV1eDgYFRU1Eq0GHiZb926dfXqVY1G4yyqh6Joe3s7WEojMzNzfn7+1q1bXC43ISHBeaChoSGDwbCo/xcsDunOtU0gKwdqMQSyHB4eHikpKQqFwrX6AXAdEASxch2k0Wjh4eHFxcWlpaWuwkqSJEEQIKAbx/G7d+9GRkY617Kx2+2tra1gxS/X1kAuYkhISHBwMNTiZwOoxRDIkmAYFhoauvryb8DbsGnTpmW2AQUkh4eHc3JyZmZmRkdH5XI5KOCw1IoKPB7PVYjB6ukGg4EgCKPRCPR9lT2H/GBALYZA3AVQi0ej0Vy/fh2UvwE1zx64I4jN+PLLL4eGhnp6eths9ieffBITEwOWlXnyHYc8BqAWQyBuAYZhIpHo7/7u7/R6vbe3d1JS0kPtThCExWIJDAx85ZVXgBk+Nzf35HJSII8dWKcNAnEXQNAxSZI0Gu1hvcAgYA75Sykl4FBmMpnPzBJEzzxQiyEQCGTtge9MCAQCWXugFkMgEMjaA7UYAoFA1h6oxRAIBLL2QC2GQCCQtQdqMQQCgaw9UIshEAhk7YFaDIFAIGsP1GIIBAJZe6AWQyAQyNoDtRgCgUDWHqjFEAgEsvZALYZAIJC1B2oxBAKBrD1QiyEQCGTtgVoMgUAgaw/UYggEAll7oBZDIBDI2vP/AGUG5uQeAkVXAAAAAElFTkSuQmCC"}}},{"cell_type":"markdown","source":"# Importing the libraries ","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.naive_bayes import GaussianNB","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.068132Z","iopub.execute_input":"2022-07-07T02:07:25.068606Z","iopub.status.idle":"2022-07-07T02:07:25.075706Z","shell.execute_reply.started":"2022-07-07T02:07:25.068572Z","shell.execute_reply":"2022-07-07T02:07:25.074Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Reading the dataset","metadata":{}},{"cell_type":"code","source":"dataframe = pd.read_csv(\"../input/titanic/train.csv\")\ntest_dataframe = pd.read_csv(\"../input/titanic/test.csv\")\npassangerId = test_dataframe[\"PassengerId\"]\n","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.149722Z","iopub.execute_input":"2022-07-07T02:07:25.150708Z","iopub.status.idle":"2022-07-07T02:07:25.169494Z","shell.execute_reply.started":"2022-07-07T02:07:25.150651Z","shell.execute_reply":"2022-07-07T02:07:25.168682Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Taking only the independent and useful data into the final data frame","metadata":{}},{"cell_type":"markdown","source":"## Name, Ticket , Passanger ID have almost no correlation to the outcome","metadata":{}},{"cell_type":"code","source":"final_dataframe= dataframe[['Survived', 'Pclass', 'Sex', 'Age', 'SibSp',\n       'Parch', 'Fare', 'Embarked']]\nfinal_dataframe = final_dataframe.dropna()\nfinal_dataframe.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.238226Z","iopub.execute_input":"2022-07-07T02:07:25.238615Z","iopub.status.idle":"2022-07-07T02:07:25.26737Z","shell.execute_reply.started":"2022-07-07T02:07:25.238584Z","shell.execute_reply":"2022-07-07T02:07:25.265893Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Labeling the values in the “Sex” column of the dataset to numbers","metadata":{}},{"cell_type":"code","source":"final_dataframe[\"Sex\"] = final_dataframe[\"Sex\"].replace(to_replace=final_dataframe[\"Sex\"].unique(), value = [1 , 0])","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.317046Z","iopub.execute_input":"2022-07-07T02:07:25.317511Z","iopub.status.idle":"2022-07-07T02:07:25.327587Z","shell.execute_reply.started":"2022-07-07T02:07:25.317475Z","shell.execute_reply":"2022-07-07T02:07:25.326211Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# One hot encoding\nThis is an encoding algorithm in the sklearn library to get categorical data into various columns and make encode it in a way that the dataset can be sent to the machine learning model ","metadata":{}},{"cell_type":"code","source":"final_dataframe = pd.get_dummies(final_dataframe, drop_first=True) ","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.395348Z","iopub.execute_input":"2022-07-07T02:07:25.396248Z","iopub.status.idle":"2022-07-07T02:07:25.407147Z","shell.execute_reply.started":"2022-07-07T02:07:25.396206Z","shell.execute_reply":"2022-07-07T02:07:25.405764Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Creating the training and testing datasets","metadata":{}},{"cell_type":"code","source":"train_y = final_dataframe[\"Survived\"]\ntrain_x = final_dataframe[['Pclass', 'Sex', 'Age', 'SibSp',\n       'Parch', 'Fare', 'Embarked_Q','Embarked_S']]","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.453011Z","iopub.execute_input":"2022-07-07T02:07:25.454017Z","iopub.status.idle":"2022-07-07T02:07:25.461935Z","shell.execute_reply.started":"2022-07-07T02:07:25.453965Z","shell.execute_reply":"2022-07-07T02:07:25.460622Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\ntrain_data, val_data, train_target, val_target = train_test_split(train_x,train_y, train_size=0.8)","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.49386Z","iopub.execute_input":"2022-07-07T02:07:25.494502Z","iopub.status.idle":"2022-07-07T02:07:25.501691Z","shell.execute_reply.started":"2022-07-07T02:07:25.494468Z","shell.execute_reply":"2022-07-07T02:07:25.500438Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = GaussianNB()\nmodel.fit(train_data,train_target)\nval_pred= model.predict(val_data)","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.536736Z","iopub.execute_input":"2022-07-07T02:07:25.537218Z","iopub.status.idle":"2022-07-07T02:07:25.549178Z","shell.execute_reply.started":"2022-07-07T02:07:25.537182Z","shell.execute_reply":"2022-07-07T02:07:25.54781Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import accuracy_score\n\nprint('Model accuracy score: {0:0.4f}'. format(accuracy_score(val_target, val_pred)*100)+ \"%\")","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:08:40.975535Z","iopub.execute_input":"2022-07-07T02:08:40.976017Z","iopub.status.idle":"2022-07-07T02:08:40.984941Z","shell.execute_reply.started":"2022-07-07T02:08:40.975981Z","shell.execute_reply":"2022-07-07T02:08:40.983362Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Working on the Test Dataset","metadata":{}},{"cell_type":"code","source":"final_test_dataframe =test_dataframe[['Pclass', 'Sex', 'Age', 'SibSp',\n       'Parch', 'Fare', 'Embarked']].copy()","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.636332Z","iopub.execute_input":"2022-07-07T02:07:25.637156Z","iopub.status.idle":"2022-07-07T02:07:25.644811Z","shell.execute_reply.started":"2022-07-07T02:07:25.637116Z","shell.execute_reply":"2022-07-07T02:07:25.643241Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Fill na values with mean values from corresponding columns","metadata":{}},{"cell_type":"code","source":"age_mean = final_test_dataframe.Age.mean()\nfare_mean = final_test_dataframe.Fare.mean()\nfinal_test_dataframe.fillna({\"Age\":age_mean,\"Fare\":fare_mean},inplace=True)","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.707996Z","iopub.execute_input":"2022-07-07T02:07:25.709494Z","iopub.status.idle":"2022-07-07T02:07:25.718684Z","shell.execute_reply.started":"2022-07-07T02:07:25.709427Z","shell.execute_reply":"2022-07-07T02:07:25.717316Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# One Hot Encoding and Labelling the test dataset","metadata":{}},{"cell_type":"code","source":"final_test_dataframe = pd.get_dummies(final_test_dataframe,columns=[\"Embarked\"],drop_first=True) \nfinal_test_dataframe[\"Sex\"] = final_test_dataframe[\"Sex\"].replace(to_replace=final_test_dataframe[\"Sex\"].unique(), value = [1 , 0])","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.782471Z","iopub.execute_input":"2022-07-07T02:07:25.783118Z","iopub.status.idle":"2022-07-07T02:07:25.794957Z","shell.execute_reply.started":"2022-07-07T02:07:25.783084Z","shell.execute_reply":"2022-07-07T02:07:25.794009Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train Test Split","metadata":{}},{"cell_type":"code","source":"train_y = final_dataframe[\"Survived\"]\ntrain_x = final_dataframe[['Pclass', 'Sex', 'Age', 'SibSp',\n       'Parch', 'Fare', 'Embarked_Q','Embarked_S']]\n\ntest_x = final_test_dataframe","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.903211Z","iopub.execute_input":"2022-07-07T02:07:25.903903Z","iopub.status.idle":"2022-07-07T02:07:25.911095Z","shell.execute_reply.started":"2022-07-07T02:07:25.90387Z","shell.execute_reply":"2022-07-07T02:07:25.909755Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#  Training the Model and Getting Predictions","metadata":{}},{"cell_type":"code","source":"model = GaussianNB()\n\nmodel.fit(train_x, train_y)\n\npredictions = model.predict(test_x)","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:25.980007Z","iopub.execute_input":"2022-07-07T02:07:25.98045Z","iopub.status.idle":"2022-07-07T02:07:25.993369Z","shell.execute_reply.started":"2022-07-07T02:07:25.980417Z","shell.execute_reply":"2022-07-07T02:07:25.991867Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submitting the results to the Competition","metadata":{}},{"cell_type":"code","source":"results = pd.DataFrame({\"PassengerId\":passangerId,\"Survived\":predictions})\nresults.to_csv(\"submissions.csv\",index=False)","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:26.103062Z","iopub.execute_input":"2022-07-07T02:07:26.104049Z","iopub.status.idle":"2022-07-07T02:07:26.113877Z","shell.execute_reply.started":"2022-07-07T02:07:26.104005Z","shell.execute_reply":"2022-07-07T02:07:26.112286Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"results.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-07T02:07:46.472447Z","iopub.execute_input":"2022-07-07T02:07:46.472914Z","iopub.status.idle":"2022-07-07T02:07:46.486407Z","shell.execute_reply.started":"2022-07-07T02:07:46.472878Z","shell.execute_reply":"2022-07-07T02:07:46.484872Z"},"trusted":true},"execution_count":null,"outputs":[]}]}