disease_prediction.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "import boto3, re, sys, math, json, os, sagemaker, urllib.request, csv\n",
    "from sagemaker import get_execution_role\n",
    "import numpy as np                                \n",
    "import pandas as pd                               \n",
    "import matplotlib.pyplot as plt                                 \n",
    "from time import gmtime, strftime                 \n",
    "from sagemaker.predictor import csv_serializer \n",
    "\n",
    "from sklearn.preprocessing import MultiLabelBinarizer, LabelEncoder\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.multiclass import OneVsRestClassifier\n",
    "from sklearn.externals import joblib\n",
    "\n",
    "from io import StringIO"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols_list = ['gender_categorized','age_binned','blood_pressure','pulse_rate_categorized','respiration_rate_categorized',\n",
    "             'BODY_TEMPERATURE','BODY_WEIGHT','HEIGHT','SPO2_categorized'] #'district_categorized',\n",
    "vitals =['SYSTOLIC_BP','DIASTOLIC_BP','PULSE','RESPIRATION_RATE','BODY_TEMPERATURE','BODY_WEIGHT','HEIGHT','SPO2']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "def drop_unnecessary_cols(df):\n",
    "\n",
    "    df.drop(columns=['HEART_RATE','HEAD_CIRCUMFERENCE','UPPER_ARM_CIRCUMFERENCE'],inplace = True)\n",
    "    df = df[pd.notnull(df['DISEASE_ID'])]\n",
    "    #df.drop(df[df.REFERRED == 'Y'].index, inplace=True)\n",
    "    df.drop(df[df.DISEASE_ID == '0'].index, inplace=True)\n",
    "    df = df[df.SYMPTOM_ID.notnull()]\n",
    "    df[vitals] = df[vitals].replace(0, np.nan)\n",
    "    df.drop(df[df.DISEASE_ID == 'Confusion'].index, inplace=True)\n",
    "\n",
    "    return df\n",
    "\n",
    "def drop_wrong_vitals(df):\n",
    "\n",
    "    df.drop(df[(df.SYSTOLIC_BP>230) | (df.DIASTOLIC_BP>150)].index, inplace = True)\n",
    "    df.drop(df[(df.SYSTOLIC_BP<80) | (df.DIASTOLIC_BP<50)].index, inplace=True)\n",
    "    df.drop(df[(df.BODY_TEMPERATURE<90) | (df.BODY_TEMPERATURE>110)].index, inplace=True)\n",
    "    df.drop(df[df.AGE>100].index, inplace=True)\n",
    "    df.drop(df[(df.SPO2>100) | (df.SPO2<80)].index,inplace=True)\n",
    "    df.drop(df[(df.PULSE<50) | (df.PULSE>120)].index,inplace=True)\n",
    "    df.drop(df[(df.RESPIRATION_RATE>30) | (df.RESPIRATION_RATE<13)].index,inplace=True)\n",
    "    df.drop(df[df.BODY_WEIGHT>200].index,inplace=True)\n",
    "    df.drop(df[(df.HEIGHT>200) | (df.HEIGHT<45)].index,inplace=True)\n",
    "\n",
    "    return df\n",
    "\n",
    "def bin_ages(df):\n",
    "\n",
    "    bins = [x for x in range(0,101,5)]\n",
    "    labels = [x for x in range(1,21)]\n",
    "    df['age_binned'] = pd.cut(df.AGE,bins,labels=labels,include_lowest=True)\n",
    "    \n",
    "    return df\n",
    "\n",
    "def fill_nas(df):\n",
    "    \n",
    "    '''WARNING: These values need to be entered as per the median of data'''\n",
    "\n",
    "    df.SYSTOLIC_BP.fillna(120,inplace=True)\n",
    "    df.DIASTOLIC_BP.fillna(80,inplace=True)\n",
    "    df.PULSE.fillna(84,inplace=True)\n",
    "    df.RESPIRATION_RATE.fillna(18,inplace=True)\n",
    "    df.BODY_TEMPERATURE.fillna(98.2,inplace=True)\n",
    "    df.BODY_WEIGHT.fillna(45,inplace=True)\n",
    "    df.HEIGHT.fillna(151,inplace=True)\n",
    "    df.SPO2.fillna(99,inplace=True)\n",
    "\n",
    "    return df\n",
    "\n",
    "def categorize_bp(df):\n",
    "\n",
    "    df['blood_pressure']=0\n",
    "    df['blood_pressure'][(df.SYSTOLIC_BP<90) | (df.DIASTOLIC_BP<60)] = 0\n",
    "    df['blood_pressure'][((df.SYSTOLIC_BP>=90) & (df.SYSTOLIC_BP<=120)) & ((df.DIASTOLIC_BP>=60) & (df.DIASTOLIC_BP<=80))] = 1\n",
    "    df['blood_pressure'][((df.SYSTOLIC_BP>120) & (df.SYSTOLIC_BP<130)) & ((df.DIASTOLIC_BP>=60) & (df.DIASTOLIC_BP<=80))] = 2\n",
    "    df['blood_pressure'][((df.SYSTOLIC_BP>=130) & (df.SYSTOLIC_BP<140)) | ((df.DIASTOLIC_BP>80) & (df.DIASTOLIC_BP<90))] = 3\n",
    "    df['blood_pressure'][((df.SYSTOLIC_BP>=140) & (df.SYSTOLIC_BP<180)) | ((df.DIASTOLIC_BP>=90) & (df.DIASTOLIC_BP<120))] = 4\n",
    "    df['blood_pressure'][(df.SYSTOLIC_BP>=180) | (df.DIASTOLIC_BP>=120)] = 5\n",
    "\n",
    "    return df\n",
    "\n",
    "def categorize_pulse_rate(df):\n",
    "    \n",
    "    df['pulse_rate_categorized']=0\n",
    "    df['pulse_rate_categorized'][df.PULSE<60]=0\n",
    "    df['pulse_rate_categorized'][(df.PULSE>=60) & (df.PULSE<=100)]=1\n",
    "    df['pulse_rate_categorized'][df.PULSE>100]=2\n",
    "\n",
    "    return df\n",
    "\n",
    "def categorize_respiration_rate(df):\n",
    "\n",
    "    df['respiration_rate_categorized']=0\n",
    "    df['respiration_rate_categorized'][df.RESPIRATION_RATE<16]=0\n",
    "    df['respiration_rate_categorized'][(df.RESPIRATION_RATE>=16) & (df.RESPIRATION_RATE<=20)]=1\n",
    "    df['respiration_rate_categorized'][df.RESPIRATION_RATE>20]=2\n",
    "\n",
    "    return df\n",
    "\n",
    "def categorize_spo2(df):\n",
    "\n",
    "    df['SPO2_categorized']=0\n",
    "    df['SPO2_categorized'][df.SPO2>=95]=1\n",
    "    df['SPO2_categorized'][df.SPO2<95]=0\n",
    "\n",
    "    return df\n",
    "\n",
    "def categorize_gender(df):\n",
    "\n",
    "    df['gender_categorized'] = 0\n",
    "    df['gender_categorized'][df.GENDER == 'Male'] = 0\n",
    "    df['gender_categorized'][df.GENDER == 'Female'] = 1\n",
    "\n",
    "    return df\n",
    "\n",
    "def categorize_district(df):\n",
    "        \n",
    "    label_enc_district = LabelEncoder()\n",
    "    df['district_categorized'] = label_enc_district.fit_transform(df.DISTRICT_NAME)\n",
    "\n",
    "    return df\n",
    "\n",
    "def encode_symptoms(df):\n",
    "\n",
    "    df.SYMPTOM_ID = [[symptom for symptom in symptoms_row if symptom!=''] for symptoms_row in df.SYMPTOM_ID.str.split('~').tolist()]\n",
    "    \n",
    "    symptoms_encoded = []\n",
    "                    \n",
    "    mlb_symtoms = MultiLabelBinarizer()\n",
    "    symptoms_encoded = mlb_symtoms.fit_transform(df.SYMPTOM_ID)        \n",
    "        \n",
    "    df['symptoms_encoded'] = symptoms_encoded.tolist()\n",
    "    \n",
    "    return df, symptoms_encoded\n",
    "\n",
    "def encode_diseases(df):\n",
    "\n",
    "    df.DISEASE_ID = (df.DISEASE_ID.str.split('~'))\n",
    "    mlb_diseases = MultiLabelBinarizer()\n",
    "    diseases_encoded = mlb_diseases.fit_transform(df.DISEASE_ID)\n",
    "        \n",
    "    df['diseases_encoded'] = diseases_encoded.tolist()\n",
    "\n",
    "    return df, diseases_encoded\n",
    "\n",
    "def format_data(df):\n",
    "\n",
    "    df = drop_unnecessary_cols(df)\n",
    "    df = drop_wrong_vitals(df)\n",
    "    df = fill_nas(df)\n",
    "    return df\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_data = pd.read_excel('ML DATA 03012020.xlsx')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PATIENT_VISIT_ID</th>\n",
       "      <th>GENDER</th>\n",
       "      <th>AGE</th>\n",
       "      <th>STATE_NAME</th>\n",
       "      <th>DISTRICT_NAME</th>\n",
       "      <th>DISEASE_ID</th>\n",
       "      <th>SYMPTOM_ID</th>\n",
       "      <th>SYSTOLIC_BP</th>\n",
       "      <th>DIASTOLIC_BP</th>\n",
       "      <th>PULSE</th>\n",
       "      <th>RESPIRATION_RATE</th>\n",
       "      <th>BODY_TEMPERATURE</th>\n",
       "      <th>BODY_WEIGHT</th>\n",
       "      <th>HEART_RATE</th>\n",
       "      <th>HEIGHT</th>\n",
       "      <th>HEAD_CIRCUMFERENCE</th>\n",
       "      <th>UPPER_ARM_CIRCUMFERENCE</th>\n",
       "      <th>SPO2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>PV000000183054</td>\n",
       "      <td>Female</td>\n",
       "      <td>18.0</td>\n",
       "      <td>Orissa</td>\n",
       "      <td>NABARANGAPUR</td>\n",
       "      <td>DISE02857</td>\n",
       "      <td>SYMP00756~SYMP00875~~~~~~~~~</td>\n",
       "      <td>110.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>19.0</td>\n",
       "      <td>101.3</td>\n",
       "      <td>45.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>120.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>PV000000191142</td>\n",
       "      <td>Male</td>\n",
       "      <td>24.0</td>\n",
       "      <td>Orissa</td>\n",
       "      <td>NABARANGAPUR</td>\n",
       "      <td>DISE18070</td>\n",
       "      <td>SYMP00103~SYMP01220~~~~~~~~~</td>\n",
       "      <td>120.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>98.6</td>\n",
       "      <td>45.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>153.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>PV000000165538</td>\n",
       "      <td>Male</td>\n",
       "      <td>14.0</td>\n",
       "      <td>Orissa</td>\n",
       "      <td>NABARANGAPUR</td>\n",
       "      <td>DISE03581</td>\n",
       "      <td>SYMP00875~SYMP03669~~~~~~~~~</td>\n",
       "      <td>80.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>96.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>98.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>164.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>PV000000175974</td>\n",
       "      <td>Male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>Orissa</td>\n",
       "      <td>NABARANGAPUR</td>\n",
       "      <td>DISE04688</td>\n",
       "      <td>SYMP01641~SYMP01207~~~~~~~~~</td>\n",
       "      <td>120.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>98.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>165.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>PV000000181454</td>\n",
       "      <td>Male</td>\n",
       "      <td>25.0</td>\n",
       "      <td>Orissa</td>\n",
       "      <td>NABARANGAPUR</td>\n",
       "      <td>DISE02587</td>\n",
       "      <td>SYMP00823~SYMP00829~~~~~~~~~</td>\n",
       "      <td>120.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>98.0</td>\n",
       "      <td>53.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>154.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  PATIENT_VISIT_ID  GENDER   AGE STATE_NAME DISTRICT_NAME DISEASE_ID  \\\n",
       "0   PV000000183054  Female  18.0     Orissa  NABARANGAPUR  DISE02857   \n",
       "1   PV000000191142    Male  24.0     Orissa  NABARANGAPUR  DISE18070   \n",
       "2   PV000000165538    Male  14.0     Orissa  NABARANGAPUR  DISE03581   \n",
       "3   PV000000175974    Male  54.0     Orissa  NABARANGAPUR  DISE04688   \n",
       "4   PV000000181454    Male  25.0     Orissa  NABARANGAPUR  DISE02587   \n",
       "\n",
       "                     SYMPTOM_ID  SYSTOLIC_BP  DIASTOLIC_BP  PULSE  \\\n",
       "0  SYMP00756~SYMP00875~~~~~~~~~        110.0          70.0  114.0   \n",
       "1  SYMP00103~SYMP01220~~~~~~~~~        120.0          80.0   70.0   \n",
       "2  SYMP00875~SYMP03669~~~~~~~~~         80.0          60.0   96.0   \n",
       "3  SYMP01641~SYMP01207~~~~~~~~~        120.0          80.0   95.0   \n",
       "4  SYMP00823~SYMP00829~~~~~~~~~        120.0          80.0   81.0   \n",
       "\n",
       "   RESPIRATION_RATE  BODY_TEMPERATURE  BODY_WEIGHT  HEART_RATE  HEIGHT  \\\n",
       "0              19.0             101.3         45.0         NaN   120.0   \n",
       "1              18.0              98.6         45.0         NaN   153.0   \n",
       "2              20.0              98.0          0.0         NaN   164.0   \n",
       "3              20.0              98.0          0.0         NaN   165.0   \n",
       "4              18.0              98.0         53.0         NaN   154.0   \n",
       "\n",
       "   HEAD_CIRCUMFERENCE  UPPER_ARM_CIRCUMFERENCE  SPO2  \n",
       "0                 NaN                      NaN   NaN  \n",
       "1                 NaN                      NaN   NaN  \n",
       "2                 NaN                      NaN   NaN  \n",
       "3                 NaN                      NaN   NaN  \n",
       "4                 NaN                      NaN   NaN  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_data = format_data(test_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>PATIENT_VISIT_ID</th>\n",
       "      <th>GENDER</th>\n",
       "      <th>AGE</th>\n",
       "      <th>STATE_NAME</th>\n",
       "      <th>DISTRICT_NAME</th>\n",
       "      <th>DISEASE_ID</th>\n",
       "      <th>SYMPTOM_ID</th>\n",
       "      <th>SYSTOLIC_BP</th>\n",
       "      <th>DIASTOLIC_BP</th>\n",
       "      <th>PULSE</th>\n",
       "      <th>RESPIRATION_RATE</th>\n",
       "      <th>BODY_TEMPERATURE</th>\n",
       "      <th>BODY_WEIGHT</th>\n",
       "      <th>HEIGHT</th>\n",
       "      <th>SPO2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>PV000000183054</td>\n",
       "      <td>Female</td>\n",
       "      <td>18.0</td>\n",
       "      <td>Orissa</td>\n",
       "      <td>NABARANGAPUR</td>\n",
       "      <td>DISE02857</td>\n",
       "      <td>SYMP00756~SYMP00875~~~~~~~~~</td>\n",
       "      <td>110.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>114.0</td>\n",
       "      <td>19.0</td>\n",
       "      <td>101.3</td>\n",
       "      <td>45.0</td>\n",
       "      <td>120.0</td>\n",
       "      <td>99.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>PV000000191142</td>\n",
       "      <td>Male</td>\n",
       "      <td>24.0</td>\n",
       "      <td>Orissa</td>\n",
       "      <td>NABARANGAPUR</td>\n",
       "      <td>DISE18070</td>\n",
       "      <td>SYMP00103~SYMP01220~~~~~~~~~</td>\n",
       "      <td>120.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>98.6</td>\n",
       "      <td>45.0</td>\n",
       "      <td>153.0</td>\n",
       "      <td>99.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>PV000000165538</td>\n",
       "      <td>Male</td>\n",
       "      <td>14.0</td>\n",
       "      <td>Orissa</td>\n",
       "      <td>NABARANGAPUR</td>\n",
       "      <td>DISE03581</td>\n",
       "      <td>SYMP00875~SYMP03669~~~~~~~~~</td>\n",
       "      <td>80.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>96.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>98.0</td>\n",
       "      <td>45.0</td>\n",
       "      <td>164.0</td>\n",
       "      <td>99.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>PV000000175974</td>\n",
       "      <td>Male</td>\n",
       "      <td>54.0</td>\n",
       "      <td>Orissa</td>\n",
       "      <td>NABARANGAPUR</td>\n",
       "      <td>DISE04688</td>\n",
       "      <td>SYMP01641~SYMP01207~~~~~~~~~</td>\n",
       "      <td>120.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>95.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>98.0</td>\n",
       "      <td>45.0</td>\n",
       "      <td>165.0</td>\n",
       "      <td>99.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>PV000000181454</td>\n",
       "      <td>Male</td>\n",
       "      <td>25.0</td>\n",
       "      <td>Orissa</td>\n",
       "      <td>NABARANGAPUR</td>\n",
       "      <td>DISE02587</td>\n",
       "      <td>SYMP00823~SYMP00829~~~~~~~~~</td>\n",
       "      <td>120.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>98.0</td>\n",
       "      <td>53.0</td>\n",
       "      <td>154.0</td>\n",
       "      <td>99.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  PATIENT_VISIT_ID  GENDER   AGE STATE_NAME DISTRICT_NAME DISEASE_ID  \\\n",
       "0   PV000000183054  Female  18.0     Orissa  NABARANGAPUR  DISE02857   \n",
       "1   PV000000191142    Male  24.0     Orissa  NABARANGAPUR  DISE18070   \n",
       "2   PV000000165538    Male  14.0     Orissa  NABARANGAPUR  DISE03581   \n",
       "3   PV000000175974    Male  54.0     Orissa  NABARANGAPUR  DISE04688   \n",
       "4   PV000000181454    Male  25.0     Orissa  NABARANGAPUR  DISE02587   \n",
       "\n",
       "                     SYMPTOM_ID  SYSTOLIC_BP  DIASTOLIC_BP  PULSE  \\\n",
       "0  SYMP00756~SYMP00875~~~~~~~~~        110.0          70.0  114.0   \n",
       "1  SYMP00103~SYMP01220~~~~~~~~~        120.0          80.0   70.0   \n",
       "2  SYMP00875~SYMP03669~~~~~~~~~         80.0          60.0   96.0   \n",
       "3  SYMP01641~SYMP01207~~~~~~~~~        120.0          80.0   95.0   \n",
       "4  SYMP00823~SYMP00829~~~~~~~~~        120.0          80.0   81.0   \n",
       "\n",
       "   RESPIRATION_RATE  BODY_TEMPERATURE  BODY_WEIGHT  HEIGHT  SPO2  \n",
       "0              19.0             101.3         45.0   120.0  99.0  \n",
       "1              18.0              98.6         45.0   153.0  99.0  \n",
       "2              20.0              98.0         45.0   164.0  99.0  \n",
       "3              20.0              98.0         45.0   165.0  99.0  \n",
       "4              18.0              98.0         53.0   154.0  99.0  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_data.head(1000).to_csv(\"Test DF.csv\", index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Success - the MySageMakerInstance is in the us-east-1 region.\n"
     ]
    }
   ],
   "source": [
    "# Define IAM role\n",
    "role = get_execution_role()\n",
    "\n",
    "my_region = boto3.session.Session().region_name # set the region of the instance\n",
    "print(\"Success - the MySageMakerInstance is in the \" + my_region + \" region.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "endpoint_new = 'sagemaker-scikit-learn-2020-01-07-07-13-43-598'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor = sagemaker.predictor.RealTimePredictor(\n",
    "    endpoint = endpoint_new,\n",
    "    content_type='text/csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Actual:DISE02857\tPredicted:{\"diseases\": [\"DISE02857\", \"DISE19879\"]}\n",
      "Actual:DISE18070\tPredicted:{\"diseases\": [\"DISE02386\", \"DISE18070\"]}\n",
      "Actual:DISE03581\tPredicted:{\"diseases\": [\"DISE03581\"]}\n",
      "Actual:DISE04688\tPredicted:{\"diseases\": [\"DISE04688\"]}\n",
      "Actual:DISE02587\tPredicted:{\"diseases\": [\"DISE02587\"]}\n",
      "Actual:DISE04122\tPredicted:{\"diseases\": [\"DISE04122\"]}\n",
      "Actual:DISE02120\tPredicted:{\"diseases\": [\"DISE02120\"]}\n",
      "Actual:DISE02120\tPredicted:{\"diseases\": []}\n",
      "Actual:DISE04000\tPredicted:{\"diseases\": [\"DISE04000\"]}\n",
      "Actual:DISE02534\tPredicted:{\"diseases\": [\"DISE02534\"]}\n",
      "Actual:DISE04394\tPredicted:{\"diseases\": [\"DISE04394\", \"DISE09728\"]}\n",
      "Actual:DISE02938\tPredicted:{\"diseases\": [\"DISE02938\"]}\n",
      "Actual:DISE03071\tPredicted:{\"diseases\": [\"DISE03071\"]}\n",
      "Actual:DISE02534\tPredicted:{\"diseases\": [\"DISE02534\"]}\n",
      "Actual:DISE00293\tPredicted:{\"diseases\": [\"DISE00293\"]}\n",
      "Actual:DISE02045\tPredicted:{\"diseases\": [\"DISE02045\"]}\n",
      "Actual:DISE02534\tPredicted:{\"diseases\": [\"DISE02534\"]}\n",
      "Actual:DISE09221\tPredicted:{\"diseases\": [\"DISE09221\"]}\n",
      "Actual:DISE00200\tPredicted:{\"diseases\": [\"DISE00200\"]}\n",
      "Actual:DISE02534\tPredicted:{\"diseases\": [\"DISE10654\"]}\n",
      "Actual:DISE02532\tPredicted:{\"diseases\": [\"DISE02532\"]}\n",
      "Actual:DISE18070\tPredicted:{\"diseases\": [\"DISE18070\"]}\n",
      "Actual:DISE05816\tPredicted:{\"diseases\": [\"DISE05816\"]}\n",
      "Actual:DISE09221\tPredicted:{\"diseases\": [\"DISE09221\"]}\n",
      "Actual:DISE04476\tPredicted:{\"diseases\": [\"DISE04476\"]}\n",
      "Actual:DISE02769\tPredicted:{\"diseases\": [\"DISE02769\"]}\n",
      "Actual:DISE09221\tPredicted:{\"diseases\": [\"DISE09221\"]}\n",
      "Actual:DISE04476\tPredicted:{\"diseases\": [\"DISE04476\"]}\n",
      "Actual:DISE09728\tPredicted:{\"diseases\": [\"DISE09728\"]}\n",
      "Actual:DISE04476\tPredicted:{\"diseases\": [\"DISE04476\"]}\n",
      "Actual:DISE13224\tPredicted:{\"diseases\": [\"DISE13224\"]}\n",
      "Actual:DISE02534\tPredicted:{\"diseases\": [\"DISE02534\"]}\n",
      "Actual:DISE00590\tPredicted:{\"diseases\": [\"DISE00590\"]}\n",
      "Actual:DISE02769\tPredicted:{\"diseases\": [\"DISE00872\", \"DISE02769\"]}\n",
      "Actual:DISE03900\tPredicted:{\"diseases\": [\"DISE03900\"]}\n",
      "Actual:DISE17273\tPredicted:{\"diseases\": [\"DISE17273\"]}\n",
      "Actual:DISE10782\tPredicted:{\"diseases\": [\"DISE10782\", \"DISE19879\"]}\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36m_make_request\u001b[0;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[1;32m    376\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m  \u001b[0;31m# Python 2.7, use buffering of HTTP responses\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 377\u001b[0;31m                 \u001b[0mhttplib_response\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetresponse\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbuffering\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    378\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[0;34m:\u001b[0m  \u001b[0;31m# Python 2.6 and older, Python 3\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mTypeError\u001b[0m: getresponse() got an unexpected keyword argument 'buffering'",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-34-db4485bbd026>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mline\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreadlines\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      6\u001b[0m     \u001b[0mprediction_text\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mheader\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34m'\\n'\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mline\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 7\u001b[0;31m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Actual:\"\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mline\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m','\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0;34m\"\\tPredicted:\"\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mpredictor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprediction_text\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdecode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'utf-8'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;31m#['diseases'])\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/sagemaker/predictor.py\u001b[0m in \u001b[0;36mpredict\u001b[0;34m(self, data, initial_args)\u001b[0m\n\u001b[1;32m    105\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    106\u001b[0m         \u001b[0mrequest_args\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_create_request_args\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minitial_args\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 107\u001b[0;31m         \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msagemaker_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msagemaker_runtime_client\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minvoke_endpoint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mrequest_args\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    108\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_handle_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    109\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/client.py\u001b[0m in \u001b[0;36m_api_call\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    355\u001b[0m                     \"%s() only accepts keyword arguments.\" % py_operation_name)\n\u001b[1;32m    356\u001b[0m             \u001b[0;31m# The \"self\" in this scope is referring to the BaseClient.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 357\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_api_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moperation_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    358\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    359\u001b[0m         \u001b[0m_api_call\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpy_operation_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/client.py\u001b[0m in \u001b[0;36m_make_api_call\u001b[0;34m(self, operation_name, api_params)\u001b[0m\n\u001b[1;32m    646\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    647\u001b[0m             http, parsed_response = self._make_request(\n\u001b[0;32m--> 648\u001b[0;31m                 operation_model, request_dict, request_context)\n\u001b[0m\u001b[1;32m    649\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    650\u001b[0m         self.meta.events.emit(\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/client.py\u001b[0m in \u001b[0;36m_make_request\u001b[0;34m(self, operation_model, request_dict, request_context)\u001b[0m\n\u001b[1;32m    665\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_make_request\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moperation_model\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequest_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequest_context\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    666\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 667\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_endpoint\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmake_request\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moperation_model\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequest_dict\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    668\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    669\u001b[0m             self.meta.events.emit(\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/endpoint.py\u001b[0m in \u001b[0;36mmake_request\u001b[0;34m(self, operation_model, request_dict)\u001b[0m\n\u001b[1;32m    100\u001b[0m         logger.debug(\"Making request for %s with params: %s\",\n\u001b[1;32m    101\u001b[0m                      operation_model, request_dict)\n\u001b[0;32m--> 102\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_send_request\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moperation_model\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    103\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    104\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mcreate_request\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moperation_model\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/endpoint.py\u001b[0m in \u001b[0;36m_send_request\u001b[0;34m(self, request_dict, operation_model)\u001b[0m\n\u001b[1;32m    133\u001b[0m         \u001b[0mcontext\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrequest_dict\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'context'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    134\u001b[0m         success_response, exception = self._get_response(\n\u001b[0;32m--> 135\u001b[0;31m             request, operation_model, context)\n\u001b[0m\u001b[1;32m    136\u001b[0m         while self._needs_retry(attempts, operation_model, request_dict,\n\u001b[1;32m    137\u001b[0m                                 success_response, exception):\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/endpoint.py\u001b[0m in \u001b[0;36m_get_response\u001b[0;34m(self, request, operation_model, context)\u001b[0m\n\u001b[1;32m    165\u001b[0m         \u001b[0;31m# If no exception occurs then exception is None.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    166\u001b[0m         success_response, exception = self._do_get_response(\n\u001b[0;32m--> 167\u001b[0;31m             request, operation_model)\n\u001b[0m\u001b[1;32m    168\u001b[0m         kwargs_to_emit = {\n\u001b[1;32m    169\u001b[0m             \u001b[0;34m'response_dict'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/endpoint.py\u001b[0m in \u001b[0;36m_do_get_response\u001b[0;34m(self, request, operation_model)\u001b[0m\n\u001b[1;32m    198\u001b[0m             \u001b[0mhttp_response\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfirst_non_none_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponses\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    199\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mhttp_response\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 200\u001b[0;31m                 \u001b[0mhttp_response\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_send\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    201\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mHTTPClientError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    202\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/endpoint.py\u001b[0m in \u001b[0;36m_send\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    242\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    243\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_send\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequest\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 244\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhttp_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    245\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    246\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/botocore/httpsession.py\u001b[0m in \u001b[0;36msend\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    261\u001b[0m                 \u001b[0mpreload_content\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    262\u001b[0m                 \u001b[0mdecode_content\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 263\u001b[0;31m                 \u001b[0mchunked\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_chunked\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mheaders\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    264\u001b[0m             )\n\u001b[1;32m    265\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36murlopen\u001b[0;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)\u001b[0m\n\u001b[1;32m    598\u001b[0m                                                   \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtimeout_obj\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    599\u001b[0m                                                   \u001b[0mbody\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbody\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mheaders\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 600\u001b[0;31m                                                   chunked=chunked)\n\u001b[0m\u001b[1;32m    601\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    602\u001b[0m             \u001b[0;31m# If we're going to release the connection in ``finally:``, then\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/site-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36m_make_request\u001b[0;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[1;32m    378\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[0;34m:\u001b[0m  \u001b[0;31m# Python 2.6 and older, Python 3\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    379\u001b[0m                 \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 380\u001b[0;31m                     \u001b[0mhttplib_response\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetresponse\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    381\u001b[0m                 \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    382\u001b[0m                     \u001b[0;31m# Remove the TypeError from the exception chain in Python 3;\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/http/client.py\u001b[0m in \u001b[0;36mgetresponse\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1329\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1330\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1331\u001b[0;31m                 \u001b[0mresponse\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbegin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1332\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mConnectionError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1333\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/http/client.py\u001b[0m in \u001b[0;36mbegin\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    295\u001b[0m         \u001b[0;31m# read until we get a non-100 response\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    296\u001b[0m         \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 297\u001b[0;31m             \u001b[0mversion\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstatus\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreason\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_read_status\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    298\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0mCONTINUE\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    299\u001b[0m                 \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/http/client.py\u001b[0m in \u001b[0;36m_read_status\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    256\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    257\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_read_status\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 258\u001b[0;31m         \u001b[0mline\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreadline\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_MAXLINE\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"iso-8859-1\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    259\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mline\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0m_MAXLINE\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    260\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mLineTooLong\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"status line\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/socket.py\u001b[0m in \u001b[0;36mreadinto\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m    584\u001b[0m         \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    585\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 586\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sock\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    587\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    588\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_timeout_occurred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/ssl.py\u001b[0m in \u001b[0;36mrecv_into\u001b[0;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[1;32m   1007\u001b[0m                   \u001b[0;34m\"non-zero flags not allowed in calls to recv_into() on %s\"\u001b[0m \u001b[0;34m%\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1008\u001b[0m                   self.__class__)\n\u001b[0;32m-> 1009\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnbytes\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbuffer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1010\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1011\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0msocket\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbuffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnbytes\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/ssl.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, len, buffer)\u001b[0m\n\u001b[1;32m    869\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Read on closed or unwrapped SSL socket.\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    870\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 871\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sslobj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbuffer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    872\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mSSLError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    873\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mSSL_ERROR_EOF\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msuppress_ragged_eofs\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/python3/lib/python3.6/ssl.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, len, buffer)\u001b[0m\n\u001b[1;32m    629\u001b[0m         \"\"\"\n\u001b[1;32m    630\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mbuffer\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 631\u001b[0;31m             \u001b[0mv\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sslobj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbuffer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    632\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    633\u001b[0m             \u001b[0mv\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sslobj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "f = open('Test DF.csv', 'r')\n",
    "\n",
    "header = f.readline()\n",
    "# print(cols)\n",
    "for line in f.readlines():\n",
    "    prediction_text = header + '\\n' + line\n",
    "    print(\"Actual:\"+line.split(',')[5]+\"\\tPredicted:\"+predictor.predict(prediction_text).decode('utf-8'))#['diseases'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_excel()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_python3",
   "language": "python",
   "name": "conda_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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}