Urine Data Analysis.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Urine Data Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### DESCRIPTION"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Urine specimens were analyzed in an effort to determine if certain physical characteristics of the urine might be related to the formation of calcium oxalate crystals.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This data frame contains the following columns:\n",
    "\n",
    "**r** - Indicator of the presence of calcium oxalate crystals.\n",
    "\n",
    "**gravity** - The specific gravity of the urine.\n",
    "\n",
    "**ph** - The pH reading of the urine.\n",
    "\n",
    "**osmo** - The osmolarity of the urine. Osmolarity is proportional to the concentration of molecules in solution.\n",
    "\n",
    "**cond** - The conductivity of the urine. Conductivity is proportional to the concentration of charged ions in solution.\n",
    "\n",
    "**urea** - The urea concentration in millimoles per litre.\n",
    "\n",
    "**calc** - The calcium concentration in millimoles per litre."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Source\n",
    "The data were obtained from Andrews, D.F. and Herzberg, A.M. (1985) Data: A Collection of Problems from Many Fields for the Student and Research Worker. Springer-Verlag.\n",
    "\n",
    "#### References\n",
    "Davison, A.C. and Hinkley, D.V. (1997) Bootstrap Methods and Their Application. Cambridge University Press."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Importing data and required Packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"urine.csv\",index_col=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>r</th>\n",
       "      <th>gravity</th>\n",
       "      <th>ph</th>\n",
       "      <th>osmo</th>\n",
       "      <th>cond</th>\n",
       "      <th>urea</th>\n",
       "      <th>calc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1.021</td>\n",
       "      <td>4.91</td>\n",
       "      <td>725.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>443</td>\n",
       "      <td>2.45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>1.017</td>\n",
       "      <td>5.74</td>\n",
       "      <td>577.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>296</td>\n",
       "      <td>4.49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>1.008</td>\n",
       "      <td>7.20</td>\n",
       "      <td>321.0</td>\n",
       "      <td>14.9</td>\n",
       "      <td>101</td>\n",
       "      <td>2.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>1.011</td>\n",
       "      <td>5.51</td>\n",
       "      <td>408.0</td>\n",
       "      <td>12.6</td>\n",
       "      <td>224</td>\n",
       "      <td>2.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>1.005</td>\n",
       "      <td>6.52</td>\n",
       "      <td>187.0</td>\n",
       "      <td>7.5</td>\n",
       "      <td>91</td>\n",
       "      <td>1.16</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   r  gravity    ph   osmo  cond  urea  calc\n",
       "1  0    1.021  4.91  725.0   NaN   443  2.45\n",
       "2  0    1.017  5.74  577.0  20.0   296  4.49\n",
       "3  0    1.008  7.20  321.0  14.9   101  2.36\n",
       "4  0    1.011  5.51  408.0  12.6   224  2.15\n",
       "5  0    1.005  6.52  187.0   7.5    91  1.16"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>r</th>\n",
       "      <th>gravity</th>\n",
       "      <th>ph</th>\n",
       "      <th>osmo</th>\n",
       "      <th>cond</th>\n",
       "      <th>urea</th>\n",
       "      <th>calc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>474.000000</td>\n",
       "      <td>474.000000</td>\n",
       "      <td>474.000000</td>\n",
       "      <td>468.000000</td>\n",
       "      <td>468.000000</td>\n",
       "      <td>474.000000</td>\n",
       "      <td>474.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.430380</td>\n",
       "      <td>1.018114</td>\n",
       "      <td>6.028481</td>\n",
       "      <td>615.038462</td>\n",
       "      <td>20.901282</td>\n",
       "      <td>266.405063</td>\n",
       "      <td>4.138987</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.495652</td>\n",
       "      <td>0.007201</td>\n",
       "      <td>0.720469</td>\n",
       "      <td>236.968837</td>\n",
       "      <td>7.909388</td>\n",
       "      <td>130.558973</td>\n",
       "      <td>3.242775</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.005000</td>\n",
       "      <td>4.760000</td>\n",
       "      <td>187.000000</td>\n",
       "      <td>5.100000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>0.170000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.012000</td>\n",
       "      <td>5.530000</td>\n",
       "      <td>410.000000</td>\n",
       "      <td>14.300000</td>\n",
       "      <td>159.000000</td>\n",
       "      <td>1.450000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.018000</td>\n",
       "      <td>5.940000</td>\n",
       "      <td>612.500000</td>\n",
       "      <td>21.400000</td>\n",
       "      <td>260.000000</td>\n",
       "      <td>3.160000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.024000</td>\n",
       "      <td>6.400000</td>\n",
       "      <td>803.000000</td>\n",
       "      <td>27.000000</td>\n",
       "      <td>380.000000</td>\n",
       "      <td>6.190000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.040000</td>\n",
       "      <td>7.940000</td>\n",
       "      <td>1236.000000</td>\n",
       "      <td>38.000000</td>\n",
       "      <td>620.000000</td>\n",
       "      <td>14.340000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                r     gravity          ph         osmo        cond  \\\n",
       "count  474.000000  474.000000  474.000000   468.000000  468.000000   \n",
       "mean     0.430380    1.018114    6.028481   615.038462   20.901282   \n",
       "std      0.495652    0.007201    0.720469   236.968837    7.909388   \n",
       "min      0.000000    1.005000    4.760000   187.000000    5.100000   \n",
       "25%      0.000000    1.012000    5.530000   410.000000   14.300000   \n",
       "50%      0.000000    1.018000    5.940000   612.500000   21.400000   \n",
       "75%      1.000000    1.024000    6.400000   803.000000   27.000000   \n",
       "max      1.000000    1.040000    7.940000  1236.000000   38.000000   \n",
       "\n",
       "             urea        calc  \n",
       "count  474.000000  474.000000  \n",
       "mean   266.405063    4.138987  \n",
       "std    130.558973    3.242775  \n",
       "min     10.000000    0.170000  \n",
       "25%    159.000000    1.450000  \n",
       "50%    260.000000    3.160000  \n",
       "75%    380.000000    6.190000  \n",
       "max    620.000000   14.340000  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Cleaning Data "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 474 entries, 1 to 474\n",
      "Data columns (total 7 columns):\n",
      " #   Column   Non-Null Count  Dtype  \n",
      "---  ------   --------------  -----  \n",
      " 0   r        474 non-null    int64  \n",
      " 1   gravity  474 non-null    float64\n",
      " 2   ph       474 non-null    float64\n",
      " 3   osmo     468 non-null    float64\n",
      " 4   cond     468 non-null    float64\n",
      " 5   urea     474 non-null    int64  \n",
      " 6   calc     474 non-null    float64\n",
      "dtypes: float64(5), int64(2)\n",
      "memory usage: 29.6 KB\n"
     ]
    }
   ],
   "source": [
    "# Let's see how to data looks like. Does it contains any NULL Values\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "r          0\n",
       "gravity    0\n",
       "ph         0\n",
       "osmo       6\n",
       "cond       6\n",
       "urea       0\n",
       "calc       0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>r</th>\n",
       "      <th>gravity</th>\n",
       "      <th>ph</th>\n",
       "      <th>osmo</th>\n",
       "      <th>cond</th>\n",
       "      <th>urea</th>\n",
       "      <th>calc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1.021</td>\n",
       "      <td>4.91</td>\n",
       "      <td>725.0</td>\n",
       "      <td>20.901282</td>\n",
       "      <td>443</td>\n",
       "      <td>2.45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>1.017</td>\n",
       "      <td>5.74</td>\n",
       "      <td>577.0</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>296</td>\n",
       "      <td>4.49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>1.008</td>\n",
       "      <td>7.20</td>\n",
       "      <td>321.0</td>\n",
       "      <td>14.900000</td>\n",
       "      <td>101</td>\n",
       "      <td>2.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>1.011</td>\n",
       "      <td>5.51</td>\n",
       "      <td>408.0</td>\n",
       "      <td>12.600000</td>\n",
       "      <td>224</td>\n",
       "      <td>2.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>1.005</td>\n",
       "      <td>6.52</td>\n",
       "      <td>187.0</td>\n",
       "      <td>7.500000</td>\n",
       "      <td>91</td>\n",
       "      <td>1.16</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   r  gravity    ph   osmo       cond  urea  calc\n",
       "1  0    1.021  4.91  725.0  20.901282   443  2.45\n",
       "2  0    1.017  5.74  577.0  20.000000   296  4.49\n",
       "3  0    1.008  7.20  321.0  14.900000   101  2.36\n",
       "4  0    1.011  5.51  408.0  12.600000   224  2.15\n",
       "5  0    1.005  6.52  187.0   7.500000    91  1.16"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Null Values can be replaced with mean of the entries in this dataset\n",
    "osmo = df['osmo'].mean()\n",
    "cond = df['cond'].mean()\n",
    "df['osmo'] = df['osmo'].replace(np.nan, osmo)\n",
    "df['cond'] = df['cond'].replace(np.nan, cond)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 474 entries, 1 to 474\n",
      "Data columns (total 7 columns):\n",
      " #   Column   Non-Null Count  Dtype  \n",
      "---  ------   --------------  -----  \n",
      " 0   r        474 non-null    int64  \n",
      " 1   gravity  474 non-null    float64\n",
      " 2   ph       474 non-null    float64\n",
      " 3   osmo     474 non-null    float64\n",
      " 4   cond     474 non-null    float64\n",
      " 5   urea     474 non-null    int64  \n",
      " 6   calc     474 non-null    float64\n",
      "dtypes: float64(5), int64(2)\n",
      "memory usage: 29.6 KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note - There are many other ways to clean the data. Replacing Null values with mean values is one of them."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Visualising data and spotting Trends"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.569620253164557"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "count = df['r'][df['r'] == 0].count()/df['r'].count()\n",
    "count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "270"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "count_urea = df['urea'][df['r']==0].count()\n",
    "count_urea"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0xe086acf88>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(df.corr(),cmap = 'Blues', annot=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Plotting Box Plots for Various Parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0xe0a6c6208>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# PLot Box PLot for Urea concentration\n",
    "df.boxplot(column = 'urea')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0xe0a72b688>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.boxplot(column = 'calc')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0xe0a64c308>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.boxplot(column = 'ph')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0xe0a815a88>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.boxplot(column = 'osmo')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0xe0a877fc8>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.boxplot(column = 'cond')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0xe0a8f0e08>"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df.boxplot(column='gravity')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Note**-\n",
    "As we have seen a few outliers in some of the parameters, these outliers are still within range. For example- ph of 8 is an outlier to this dataset but this data can occur as ph is generally between 1-14."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Note** - Calcium Concentration has a few outliers depending on the data but the outliers are still possible and thus cannot be discarded."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Plotting r vs all other parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0a98a148>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['r'],df['urea'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0a9f0a48>"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['r'],df['calc'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0aa5a408>"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['r'],df['ph'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0aabce08>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['r'],df['osmo'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0ab27048>"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['r'],df['cond'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0ab8d308>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['r'],df['gravity'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Plotting specific gravity of urea solution v/s other parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0abf2cc8>"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['gravity'],df['urea'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0ac60208>"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['gravity'],df['calc'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0accb288>"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXIAAAD4CAYAAADxeG0DAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjMsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+AADFEAAAUKElEQVR4nO3dfawld1nA8e9DLYUITVt7wdJ2uaIIGFK2cG1KGkktoCvVAIliiMKiJAsREolIuhKTshCTxfASDAZcAkINrwJK05a3AA2SAHoX16W1IlC3UrrpLraVNibFto9/3Km97J63OWfmnPnNfD/Jzb13zss8vz13n/Oc3zzzm8hMJEnletiqA5AkLcZELkmFM5FLUuFM5JJUOBO5JBXuJ5a5s7PPPjvX19eXuUtJKt7Bgwd/kJlr425faiJfX19nc3NzmbuUpOJFxC2TbndqRZIKZyKXpMKZyCWpcCZySSqciVySCrfUrhWpyy648jP88N77///30087hcP7dq0wImk2VuQSJydxgB/eez8XXPmZFUUkzc5ELsFJSXzadqlLTOSSVDgTuSQVzkQusXVgs852qUtM5BJweN+uk5K2XSsqhe2HUsWkrVJZkUtS4UzkklQ4E7kkFc5ELkmFM5FLUuHsWpE6yAW8VIeJXL3Qp8Q3aQGvUsekdjm1ouL1beVCF/BSXSZyFc/Ep6EzkUtS4aYm8oh4RET8Y0T8S0TcGBH7qu3vj4j/iIhD1dfO9sOV+s8FvFTXLBX5vcBlmfk0YCewKyIurm57XWburL4OtRalNEHfEp8LeKmuqV0rmZnAPdWvp1Zf2WZQUh2H9+3qVdcKuICX6omtPD3lThGnAAeBnwP+MjOviIj3A89kq2L/ArA3M+8d8dg9wB6AHTt2POOWW25pLnpJGoCIOJiZG+Nun+lgZ2ben5k7gfOAiyLiqcCfAE8GfhE4C7hizGMPZOZGZm6sra3VHoAkabJaXSuZeRdwPbArM4/mlnuBvwYuaiE+SdIUs3StrEXEGdXPjwSeA/xbRJxTbQvgBcANbQYqSRptllP0zwE+UM2TPwz4WGZeExFfjIg1IIBDwCtbjFOSNMYsXSuHgQtHbL+slYikCfrWnSI1wUWzVIyuLSblm4q6wlP0VYwuranSt4W6VDYTuTSHLr2pSCZySSqciVzF6NuaKlJTTOQqRpcWk/JNRV0y01orTdnY2MjNzc2l7U9q0/rea0/admT/5SuIRH3XyForkn7cuO4Uu1a0CiZyaQ52rahLTOSSVDgTuSQVzkQuzcGuFXWJiVyaQ5daISUXzZLmZNJWV5jI1WuuUKghcGpFveUKhRoKE7l6y15vDYWJXJIKZyKXpMKZyNVb9nprKEzk6i17vTUUU9sPI+IRwJeB06r7fzwzr4yInwE+ApwFfAN4SWb+qM1g1S0ltPZ1LR6pDbP0kd8LXJaZ90TEqcBXIuLTwB8Bb8/Mj0TEu4GXA+9qMVZ1SNeuaN+mEt6wNGxTp1Zyyz3Vr6dWXwlcBny82v4B4AWtRKhOGkprn73oKsFMc+QRcUpEHAKOAZ8HvgvclZn3VXe5FTh3zGP3RMRmRGweP368iZilpRnKG5bKNlMiz8z7M3MncB5wEfCUUXcb89gDmbmRmRtra2vzRypJGqlW10pm3gVcD1wMnBERD86xnwfc1mxo6jJb+6TumKVrZQ3438y8KyIeCTwHeDPwJeA32epc2Q18qs1A1S2H9+1q9SBg3eduIpZRz9FHHrztn8gcOSPy0B0iLmDrYOYpbFXwH8vMN0bEE3io/fCfgd/NzHsnPdfGxkZubm42Erj6a9QBRhifcOrev84+Jzmy//Ja9++CJv6ttHwRcTAzN8bdPrUiz8zDwIUjtt/M1ny51Ki6BxibOCBZN4mXWq178LafPLNTmsKzQ9V1XlhCmmJc0nauWV1hRa7OqdsR00QHTd3nKPVEIbuN+slErs6pu9hVE4tj1X2OUueaXUisn6Z2rTTJrhUtW1vTH+t7rx17W4ndLOq2aV0rVuTqrVKnP6S6PNip3mpq+mNUVX/6aaeMfZ7t1brTFloGK3JpgnFVPcx2gNBPAFoGK3JpgklV/Ylz4ePmzbt+ABRspSydiVy9NW76o6lWu3lO6++iIV0kpK+cWlFvtd1q14ckDuW2UuohVuTqtUWT9qSDmnWeQ2qTFbk0wbiqflbONWsZrMilKUYl4j6dENT2sQS1z4pcmkOf1izxtP3yeYp+gYbQKtbUGJd9FSOg96+Nlm/aKfom8sIM4QovTY1x2f9WQ3httBoLXyFI3dLHVrFZ+7HrjnHZ/1Z9fG1UBufItVJ9OalGWiUTuVbKJC4tzqmVwgy5VWzSGMcdeFymIb82Wq2pFXlEnB8RX4qImyLixoj4w2r7GyLi+xFxqPp6XvvhaqitYpPGOGmFwmUa6muj1ZulIr8PeG1mfiMiHg0cjIjPV7e9PTPf0l54GmUoiWHWE2vqJu02K+ShvDbqlqmJPDOPAkern++OiJuAc9sOTGrCidMdVsjqo1pz5BGxDlwIfB24BHh1RLwU2GSrar9zxGP2AHsAduzYsWC4Uj1dSdpDOIlLqzNz10pEPAr4BPCazPwh8C7gZ4GdbFXsbx31uMw8kJkbmbmxtrbWQMjqkz6d6j6O1w5V22ZK5BFxKltJ/IOZ+UmAzLw9M+/PzAeA9wAXtRem+moIBwg9UUhtmzq1EhEBvBe4KTPftm37OdX8OcALgRvaCVF916ekLa3CLHPklwAvAb4ZEYeqba8HXhwRO4EEjgCvaCVCSdJEs3StfAWIETdd13w4Un1dPxGn6/GpfK5+qLl1qRNj1IUejuy/fOnL2M560lLfjgOoXS5jq1Z0acnWugtvNRFjl8av/nMZW7Wi7U6MOhVsU8vbNvEcdqJoFVz9UJ1j37VUj4lcnWO1K9VjItdcunRGZt19NhFjl8Yvmcg1ly6dkTkuliP7L28txi6NX7JrRZ1jR4j04+xaUXEO79tVbN91qXGrbFbkUkP8JKG2WJFr6YZaldpto1UxkatRk3rAS03mQ31jUjnsWlGj+laVenKSSmBFPlB1q8wmqtISK9s6b0yucqhVsSIfoLpVZlNVad8rW3vLtSpW5ANUd/qjiaq0biylMmlrFUzkatThfbtGrg2+KotO5zhdohI4taJGdWmqpIkpIadLVAIr8gFqs8qsO1XSZmU7aUpo+6eGaYnZpK2usyIfoFVVmV2tbPt20FXDY0U+UKtapbCr+nbQVcMyNZFHxPnAVcBPAw8ABzLzHRFxFvBRYB04ArwoM+9sL1SVYJ5pm7b6y+t20EilmmVq5T7gtZn5FOBi4FUR8QvAXuALmflE4AvV7+qhOhdRqDtt0+aZk6NikfpoakWemUeBo9XPd0fETcC5wPOBS6u7fQC4HriilSi1UnWXla1TTTd1Sv+4+E6MZdIKhVKpas2RR8Q6cCHwdeCxVZInM49GxGPGPGYPsAdgx44di8SqFery/HbbC3WVuLSAhmXmrpWIeBTwCeA1mfnDWR+XmQcycyMzN9bW1uaJUZqoTlVf9xOAi2apBDMl8og4la0k/sHM/GS1+faIOKe6/RzgWDshqs+6fhHjvq3mqH6amsgjIoD3Ajdl5tu23XQ1sLv6eTfwqebDU9955qS0uFnmyC8BXgJ8MyIOVdteD+wHPhYRLwf+E/itdkJU3y2atOu0PLp2ivpoakWemV/JzMjMCzJzZ/V1XWb+V2Y+OzOfWH2/YxkBSyeqU9XX/QTQ9akfCbz4sjSVXStaNS++LC3IpK2uc9EsSSqciVySCufUykA57yv1h4m8R2ZNzk2d0u6bgdQNTq30RJ1TyZs4W9FT16XusCLvibZXEWxrf1qcn4xkRa4fY5VdFj8ZCUzkg1T3rESr7O7yk5HARN4bTVzFp639SWqXc+Q90cRVfNb3Xtva/iS1x0TeI8tcRbCJ/WlxruYocGpF27g2eHl8zQSufihJnTdt9UMrckkqnIlckgrnwU6tnN0v0mJM5Fqpugt4mfSlkzm1opWqc2aip6NLo5nIVQxPR5dGm5rII+J9EXEsIm7Ytu0NEfH9iDhUfT2v3TAlSePMMkf+fuCdwFUnbH97Zr6l8Yg0VZ/miT0zUVrc1ESemV+OiPX2Q9Esmrq6T5vqrvky6/1N+tJoi3StvDoiXgpsAq/NzDtH3Ski9gB7AHbs2LHA7gTdnyee541m1jcgF+qSRps3kb8LeBOQ1fe3Ar8/6o6ZeQA4AFun6M+5PxWi7Tcak7Z0srkSeWbe/uDPEfEe4JrGIpI0aH7qqm+u9sOIOGfbry8Ebhh3X0malecKzGdqRR4RHwYuBc6OiFuBK4FLI2InW1MrR4BXtBijCuIBSS2i68eAumqWrpUXj9j83hZi0Qy6nig9ICktn2utFKaERNmlWKQhMJEXqE6i7HrSl7br+ifOrvIKQT026sARdC+Z+2aj7fx7ONm0KwRZkfdYCQeOSjhTVcvl616fqx9qpUp4s5G6zopcjfOjsbRcJvIem3TgqK1k61SJtHwm8h4b16oIJ09dNJVs606VDL1LwU8vaoKJvEdmTQrre68d+fhVzEuX0BffFj+9qCkm8p4oOSl0Pb62eKBXTbFrpSe6khTGTYkMZapEWgUT+QC1mWwP79t10vMMZapEWhWnVgbo8L5dI+fJm0q2Ju3ZDP1Ar5pjRd4TdarscWs7u+bzcvnpRU1xrZUOaKprY5ZWw3FV4IOO7L+89n67YKidLxqGaWutmMhXrM2FrcY99yQlJvJSFgeT5jUtkTu1smJtdpsMpY2tKx070qqYyCWpcCZySSqciXzF2uzpHkobmychaehM5CvWZgvauOfuG9v4NHRTu1Yi4n3ArwPHMvOp1bazgI8C68AR4EWZeee0ndm10g12eUhlWbj9MCKeBdwDXLUtkf85cEdm7o+IvcCZmXnFtGBM5PW02Rtt37VUjkb6yCNiHbhmWyL/FnBpZh6NiHOA6zPzSdOex0Q+u6aqZhO2VL62+sgfm5lHAarvj5kQwJ6I2IyIzePHj8+5u+Fpojd60tK2kvqj9YOdmXkgMzcyc2Ntba3t3WkbT5SRhmHeRH57NaVC9f1YcyFJkuqYN5FfDeyuft4NfKqZcPQge6MlzWpqIo+IDwNfBZ4UEbdGxMuB/cBzI+LbwHOr39WgJnqjfTOQhsHVD3uuhK6VEmKUVsllbNVpnpwkTTctkXuptw4bQqVqZ420ONda6Sh7wCXNyoq8oyZVqkOo1CXNzoq8QH2q1O2skRZnIu+JUueUXYJWWpxTK0s267TItKvd94lJW1qMFfkS1TmAOZSLQkhanBX5EtVttRtVqU7qu5Y0TFbkhXFOWdKJrMgLZNKWtJ0V+RLZaiepDSbyJXJaRFIbnFpZMpO2pKZZkUtS4UzkklQ4E7kkFc5ELkmFM5FLUuFM5JJUOBO5JBVuoT7yiDgC3A3cD9w36eKgak6bVwjy6kNSeZqoyH85M3eaxJejzWt5ep1QqUxOrRSmzavOe0V7qUyLJvIEPhcRByNiz6g7RMSeiNiMiM3jx48vuDtJ0okWTeSXZObTgV8DXhURzzrxDpl5IDM3MnNjbW1twd1Jkk60UCLPzNuq78eAvwMuaiIojdfmUrgusyuVae5EHhE/GRGPfvBn4FeAG5oKTKO1uRSuy+xKZYrMnO+BEU9gqwqHrTbGD2Xmn016zMbGRm5ubs61P0kaqog4OKkzcO4+8sy8GXjavI+XJDXD9kNJKpyJXJIKZyKXpMKZyCWpcHN3rcy1s4jjwC1L2+HszgZ+sOogWjaEMcIwxjmEMYLj3O7xmTn2jMqlJvKuiojNvi/6NYQxwjDGOYQxguOsw6kVSSqciVySCmci33Jg1QEswRDGCMMY5xDGCI5zZs6RS1LhrMglqXAmckkqXK8TeUS8LyKORcTI5XVjy19ExHci4nBEPH3bbbsj4tvV1+7lRV3PgmP8TETcFRHXLC/i+cw7zojYGRFfjYgbq+2/vdzI61lgnI+vrtR1qBrrK5cb+ewW+Zutbj89Ir4fEe9cTsTzWfD/5v3Va3koIq6eurPM7O0X8Czg6cANY25/HvBpIICLga9X288Cbq6+n1n9fOaqx9PkGKvbng38BnDNqsfR4mv588ATq58fBxwFzlj1eFoY58OB06qfHwUcAR636vE0OcZtt78D+BDwzlWPpa1xAvfU2VevK/LM/DJwx4S7PB+4Krd8DTgjIs4BfhX4fGbekZl3Ap8HOnl1hQXGSGZ+Abh7CWEubN5xZua/Z+a3q+e4DTgGdPaagwuM80eZeW91n9Po8KftRf5mI+IZwGOBz7Uf6WIWGWddnX2xl+Rc4Hvbfr+12jZue4n6NJZJpo4zIi5iq3L97hLjatrYcUbE+RFxuLr9zdUbV4lGjjEiHga8FXjdSqJq3qS/2UdUF63/WkS8YNoTzX1hiZ6IEdtywvYS9Wksk0wcZ1Xp/A2wOzMfWFpUzRs7zsz8HnBBRDwO+PuI+Hhm3r7U6Joxbox/AFyXmd+LGHWX4kz6m92RmbdVV2L7YkR8MzPHFiBDr8hvBc7f9vt5wG0TtpeoT2OZZOw4I+J04FrgT6uPsCWb+npWlfiNwC8tMa4mjRvjM4FXR8QR4C3ASyNi//LDa8zY1zIfurD9zcD1wIWTnmjoifxqtv4YIiIuBv47M48CnwV+JSLOjIgz2bqw9GdXGegCxo2xb0aOMyIezta1Za/KzL9dbYiNGDfO8yLikQDV3+wlwLdWGegCRo4xM38nM3dk5jrwx2y9pntXGulixr2WZ0bEaQARcTZbr+W/TnqiXk+tRMSHgUuBsyPiVuBK4FSAzHw3cB1bR46/A/wP8HvVbXdExJuAf6qe6o2ZOemgxcrMO8bqsf8APBl4VPXYl2dmJ9+wFhjni9jqHvipiHhZte1lmXloacHXsMA4nwK8NSIenBp8S2Z+c7nRz2aRv9mSLPha/lVEPMBWsb0/Mycmck/Rl6TCDX1qRZKKZyKXpMKZyCWpcCZySSqciVySCmcil6TCmcglqXD/BzfRdr7yE+YkAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['gravity'],df['cond'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0ad2eac8>"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['gravity'],df['osmo'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0ad91ac8>"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['gravity'],df['ph'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Findings**-\n",
    "1. Specific gravity of urine is proportional to urea concentration.\n",
    "2. Specific gravity of urine is proportional to osmolarity of the urine."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Plotting pH of urea solution v/s other parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0adf8f48>"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD4CAYAAAAXUaZHAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjMsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+AADFEAAAXm0lEQVR4nO3df6wlZX3H8fenu4hKxRX54XZhuxgJrW1Q8AaxJIa6YvlhXf8AWVNloTTbVjS1tinrP6WYNlmTporVQFfRskb5IZWyKYgSLDEmQrwLdEXRsK4re90FrvxYolTo4rd/nLlw9txz7plzzsyZmWc+r+TmnjMz957vmXvud77zzPM8o4jAzMzS8htVB2BmZsVzcjczS5CTu5lZgpzczcwS5ORuZpag5VUHAHDkkUfGmjVrqg7DzKxRtm/f/vOIOKrfulok9zVr1jA7O1t1GGZmjSLpp4PWuVnGzCxBTu5mZglycjczS5CTu5lZgpzczcwSVIveMm1z0uW38/Szz7/w/PBDl7HjirMqjMjMUuPKfcp6EzvA088+z0mX315RRGaWIif3KetN7MOWm5mNw8ndzCxBTu5mZglycp+yww9dNtJyM7NxOLlP2Y4rzlqUyN1bxsyKlqsrpKQVwOeA3wcC+FPgR8ANwBpgN/CeiHhSkoArgXOAZ4CLIuLewiNvMCdyMytb3sr9SuD2iPgd4A3Ag8Am4M6IOAG4M3sOcDZwQva1Ebiq0IjNzGyoocld0uHAW4FrACLiuYh4ClgHXJttdi3w7uzxOmBrdNwNrJC0svDIzcxsoDyV+2uBeeALku6T9DlJhwHHRMQ+gOz70dn2q4A9XT8/ly07iKSNkmYlzc7Pz0/0JszM7GB5kvty4BTgqog4GfglLzbB9KM+y2LRgogtETETETNHHdX3RiJmZjamPMl9DpiLiHuy5zfRSfaPLjS3ZN8f69r+uK6fPxbYW0y4ZmaWx9DkHhGPAHsknZgtWgv8ANgGbMiWbQBuyR5vAy5Ux2nA/oXmGzMzm468s0J+CPiSpJcAu4CL6RwYbpR0CfAwcH627W10ukHupNMV8uJCIzYzs6FyJfeIuB+Y6bNqbZ9tA7h0wrjMzGwCHqFqZpYgJ3czswQ5uZuZJcjJ3cwsQU7uZmYJcnI3M0uQk7uZWYLyDmKyljnp8tsPumm3byhi1iyu3G2R3sQO8PSzz3PS5bdXFJGZjcrJ3RbpTezDlptZ/Ti5m5klyMndzCxBTu62yOGHLhtpuZnVj5O7LbLjirMWJXL3ljFrFneFtL6cyM2azZW7mVmCnNzNzBLk5G5mliC3uVtunpLArDlcuVsunpLArFmc3C0XT0lg1ixO7mZmCXJyNzNLUK7kLmm3pO9Jul/SbLbsCEl3SHoo+/6qbLkkfUrSTkk7JJ1S5huw6fCUBGbNMkrl/ocR8caImMmebwLujIgTgDuz5wBnAydkXxuBq4oK1qrjKQnMmmWSrpDrgDOyx9cCdwGXZcu3RkQAd0taIWllROybJFCrnhO5WXPkrdwD+Iak7ZI2ZsuOWUjY2fejs+WrgD1dPzuXLTuIpI2SZiXNzs/Pjxe9mZn1lbdyPz0i9ko6GrhD0g+X2FZ9lsWiBRFbgC0AMzMzi9abmdn4ciX3iNibfX9M0s3AqcCjC80tklYCj2WbzwHHdf34scDeAmM2K4xH3VqqhjbLSDpM0isWHgPvAB4AtgEbss02ALdkj7cBF2a9Zk4D9ru93erIo24tZXkq92OAmyUtbP/liLhd0neBGyVdAjwMnJ9tfxtwDrATeAa4uPCozQrgUbeWsqHJPSJ2AW/os/xxYG2f5QFcWkh0ZmY2Fs8Kaclye7q1macfsCTlaU/3qFtLmZO7JSlPe7pH3VrK3CxjreZEbqly5W5mliBX7pakww9d1rdppl97ui+8WopcuVuS8raneyCTpcqVuyUrT/XtgUyWKif3xLnJwayd3CyTMDc5mLVXKyv3tlSzbnIYbpQLr2ZN0rrK3dWsdfNAJktV6yp3V7PWy4ncUtS6yr1NPHeKWXu1rnJvkx1XnNX3+gLAmk23HrTM1atZWlqX3Nt2AW2UQTtO8GbpaF1yH1TNtiWx1fGaQ5v/HmZlaV1yB19AqxOfSZiVo5XJvSiuOCdXxzMJsxS4t8yYmtpf3j1ozNrByX1MTa04PWjHrB3cLNNCdUrkbeu9ZDYtrtytUj6TMCtH7spd0jJgFvhZRLxT0vHA9cARwL3A+yPiOUmHAluBNwGPAxdExO7CI6+YK87iOJGbFW+UZpm/Ah4EDs+efxz4RERcL+lq4BLgquz7kxHxOknrs+0uKDDmWmh7f/km8d/J2kgRMXwj6VjgWuCfgI8AfwzMA6+JiAOS3gL8Q0T8kaSvZ4+/I2k58AhwVCzxQjMzMzE7O1vA20lf97QBC3ZvPreCSJqhX68mSC/B5zmA+SCXHknbI2Km37q8be6fBP4O+HX2/NXAUxFxIHs+B6zKHq8C9gBk6/dn29uE+iX2pZZbc3s1jSJPt9ymdt218Q1N7pLeCTwWEdu7F/fZNHKs6/69GyXNSpqdn5/PFayZLZbnANaGg5wdLE+b++nAuySdA7yUTpv7J4EVkpZn1fmxwN5s+zngOGAua5Z5JfBE7y+NiC3AFug0y0z6RlJSx9PnOsZkZoMNTe4R8VHgowCSzgD+NiL+RNJXgPPo9JjZANyS/ci27Pl3svXfXKq93Q5Wx9PnJsz/Mujg415N1laTDGK6DLhe0j8C9wHXZMuvAb4oaSedin39ZCG2Sx1Pn+sYU7dhB5/ULzbmOYD5INc+IyX3iLgLuCt7vAs4tc82vwLOLyA267F787nuLdPHsIPPsCTdhDOTpeQ5gLnrbvt4+oGGaXsiL0Pdz0zyyJOkncjbxdMP1EwdZ22sY0xmtjQn95qp41wrdYypmw8+ZovlGqFaNo9QHcztpPlMsp/aMorV0rPUCFUn9xorO+mUfeBo0oGpSbGaLVgqufuCao2VeaGv7B4iTeuBUseYzCbh5N5SRRw4lqp2U+iBYtZkvqBqY6njSFoze5Er9xrLM6qwqrZiV+Zm9ebKvcaGdUGcpHouu/uguyeaVcuVe80tVYVPUj2XPRzdw93NquXk3mKTJNo8TUZO5GbVcbOMjaXuo1bN2s6Ve4NVPY2rE7lZfTm5N1hZ7dpuKzdrPk8/YAfxPCtmzeHpByy3afZf9xmCWXl8QdUq4RGuZuVy5W6VaNsIV5+l2LS5creDeGRp8XyWYlVw5W4HSWVkaZ3eQ9vOUqweXLnbIjuuOIvdm899oVp/+tnnWbPp1kIrzTLPEFwpmzm52wBlJ8gyR7i6UjZzs0zyxm2emEaCbFpTz7iqHkls7TQ0uUt6KfAt4NBs+5si4nJJxwPXA0cA9wLvj4jnJB0KbAXeBDwOXBARu0uKv5bq0t7btFvdpSqV6xg2vir+/nkq92eBt0XELyQdAnxb0teAjwCfiIjrJV0NXAJclX1/MiJeJ2k98HHggpLir506JdSyqu81m2594XGRH9Ki/gHqWCk7kbdXVTlhaJt7dPwie3pI9hXA24CbsuXXAu/OHq/LnpOtXytJhUVcc6m09+ZNhEW1wxfZxu8ZK61OqsoJudrcJS0DtgOvAz4D/Bh4KiIOZJvMAauyx6uAPQARcUDSfuDVwM97fudGYCPA6tWrJ3sXVrh+TQmDFPEhLfofwInc2i5Xco+I54E3SloB3Az8br/Nsu/9qvRFs5NFxBZgC3QmDssVrY1k0uaJ3gTZ3RxjZvU2Um+ZiHhK0l3AacAKScuz6v1YYG+22RxwHDAnaTnwSuCJ4kKeTNkXNurU3usLeWbVqyonDG1zl3RUVrEj6WXA24EHgf8Gzss22wDckj3elj0nW//NqMO8wkxncEvd2nsXBiQtfE16a71Rltfld5tVqV9OgPIH1g2dz13SSXQukC6jczC4MSI+Jum1vNgV8j7gfRHxbNZ18ovAyXQq9vURsWup15jWfO5LNSvs3nxu6a+fgjLPBHyWYSkr414JE83nHhE76CTq3uW7gFP7LP8VcP4YcVoDlJlsncgtZdPuNeMRqgVy5WlmddGq5F7mhY06DV6ytLmIsDxaNXGYJ6uypvOMl8017U4Drarcwe261mwuIppr2l2TW5fczfJw04eVYZqfoVY1y5TJ/bTT4aYPS4Er94KMe8rlCrF+6tz0MahTAJQ3W6c109BBTNMwrUFMdVPGoAabXN0Hu+Wd0M2fo/RNNIjJylPnCtHqK++Ebv4ctZvb3M16+PqJpcDJ3axH3SZ/MxuHm2UqVKfpgftp88XeJr3Pun+OrBqu3CtU5wrR3QGbo86fI6uOK/eK1fUf0Bd7m6WunyOrjit3M7MEObmbmSXIzTIJGzbYZal2WV+kM2s2V+6JyjOKcakLpL5IZ9ZsrtwTlffC51LbOZGbNZeTuyWhzX3yrXmm8Xl1s4w1nvvkW5NM6/Pq5J6ovBc+U7hA6j751iTT+rw6uSeq3wXRXm66MEvX0DZ3SccBW4HXAL8GtkTElZKOAG4A1gC7gfdExJOSBFwJnAM8A1wUEfeWE74txYnbrL3yXFA9APxNRNwr6RXAdkl3ABcBd0bEZkmbgE3AZcDZwAnZ15uBq7LvVrI6XlQcJaZx43effGuSaX1eR74Tk6RbgE9nX2dExD5JK4G7IuJESf+WPb4u2/5HC9sN+p1F3ompjgluGia5q1NZ+2yUmCa9K1Vb/+7WTEV9Xgu7E5OkNcDJwD3AMQsJO0vwR2ebrQL2dP3YXLbsoOQuaSOwEWD16tWjhDHQUlehU/9HH/ciTZn7bJSYJr3IlPrf19Iyjc9r7uQu6TeB/wA+HBFPd5rW+2/aZ9mi04OI2AJsgU7lnjeOpbjXxOjavM9c7VvKciV3SYfQSexfioivZosflbSyq1nmsWz5HHBc148fC+wtKmCzIqRylucDlA0ytCtk1vvlGuDBiPiXrlXbgA3Z4w3ALV3LL1THacD+pdrbrRij3PfzpMtvZ82mWwfeWLmKmKZ939IUzlg8eMuWkqef++nA+4G3Sbo/+zoH2AycKekh4MzsOcBtwC5gJ/BZ4APFh91fm29snHeirzwTii387LRiWmpb4IUD0ZpNtzpxdUnhAGXlGdosExHfpn87OsDaPtsHcOmEcY1lxxVntfo0Nc/7zJvYi9pno/yePAeiJjadmFUhuYnD/E8/vt2bz606hIOUWZm6b7ylLrnk3gZtPjspSgpneT5A2VKc3Btm0qYKJ4QXNSmR95PCAcrK4+TeMEUM9qkyIYzy2j4QDedEboM4uU9JnSqsql531LOOqg9EZk3m5D4Fbe/1Maz7ZRG3+vNBwOxgns99Cors9dG0vvx5+9UX/RoezGNt58q9YZrWVDGNATVLHTy7R+HWeT+ZFc3JvYFSS1DTOutoU1OYmZP7FIzb66NJFfq4pv2ePDTf2sLJfQrGaUpJ5SLsUge2ot7HoNdIVRsO+jY5J/cpGfWfL5VJoaZxjaDfa6QqlYO+lc/J3Uo3jaQzym37miyVg76Vz8ndktSkXkVNidOaxcm9ptow9H4azTV152YWK4sHMdXUKDe6aKJBSa1tN+UYtZmlaYPYrDqu3GsslUTez7A24jpWr3VoPplGc1Md3qdNzsndaqtOFwnr1HxS5uvV6X3aZNwsY5ZDWb1U6tbM4t446XByt0q4jbgj9WsrVh03y1gl8gw8assBwIncyuDkbpXpTmp1v4jXhq6p0J732QaKiKpjYGZmJmZnZ6sOo/XqnmCr1pb905b3mQJJ2yNipu86J3eDpYfr+x/bxuGDRPmWSu5DL6hK+rykxyQ90LXsCEl3SHoo+/6qbLkkfUrSTkk7JJ1S3NuwMrmXhBXJd8eqXp42938HPg1s7Vq2CbgzIjZL2pQ9vww4Gzgh+3ozcFX23ayRUqg+q3gPLhaqN7Ryj4hvAU/0LF4HXJs9vhZ4d9fyrdFxN7BC0sqigjWbphSqzxTeg41n3N4yx0TEPoCI2Cfp6Gz5KmBP13Zz2bJ9vb9A0kZgI8Dq1avHDMOK4l4Si01afdah6ncF3V5Fd4VUn2V9r9hGxBZgC3QuqBYch42oSVPkNkHbh/EXWSz4czmecZP7o5JWZlX7SuCxbPkccFzXdscCeycJ0KbH/zDFaXvFXFSx0PaD5CTGTe7bgA3A5uz7LV3LPyjpejoXUvcvNN+YNU0KTVVVvocikm/bD5KTyNMV8jrgO8CJkuYkXUInqZ8p6SHgzOw5wG3ALmAn8FngA6VEbTYFKcz7ksJ7sPEMrdwj4r0DVq3ts20Al04alFldjJsE61T1O5Ev1oZ2fM8tY1aCPG3ObUgwkyrjINmWdnwnd7OSLJUo2pJgJlVGL662tOM7uZtVIJUEM42zDx/sxuObdZjZWDz6td6c3M1sLE09+6jbrQ3L4uRuVoG2JJg6akv3ULe5m1XA0z1Uqw372cndrCJNTzB16stvi7lZxszG0pbmjaZy5W5mY3Miry9X7mZmCXJyNzNLkJO7mVmCnNzNzBLk5G5mliAndzOzBDm5m5klyMndzCxBTu5mZglycjczS1Cjpx/wrHpmZv01tnL3XWDMzAZrbHJv6l1gzMymoZTkLuksST+StFPSpjJew8zMBis8uUtaBnwGOBt4PfBeSa8v+nXMzGywMir3U4GdEbErIp4DrgfWFf0ivgelmdlgZST3VcCerudz2bKDSNooaVbS7Pz8/Mgv4rvAmJkNVkZXSPVZFosWRGwBtgDMzMwsWp+HE7mZWX9lVO5zwHFdz48F9pbwOmZmNkAZyf27wAmSjpf0EmA9sK2E1zEzswEKb5aJiAOSPgh8HVgGfD4ivl/065iZ2WClTD8QEbcBt5Xxu83MbLjGjlA1M7PBFDFWR5Vig5DmgZ9WHccARwI/rzqICTQ5/ibHDs2Ov8mxQ3vi/+2IOKrfilok9zqTNBsRM1XHMa4mx9/k2KHZ8Tc5dnD84GYZM7MkObmbmSXIyX24LVUHMKEmx9/k2KHZ8Tc5dnD8bnM3M0uRK3czswQ5uZuZJcjJPSNpt6TvSbpf0myf9ZL0qezuUjsknVJFnP3kiP0MSfuz9fdL+vsq4hxE0gpJN0n6oaQHJb2lZ31t9z3kir+W+1/SiV0x3S/paUkf7tmmtvs+Z/y13PcAkv5a0vclPSDpOkkv7Vl/qKQbsn1/j6Q1I71ARPirc91hN3DkEuvPAb5GZ0rj04B7qo55hNjPAP6r6jiXiO9a4M+yxy8BVjRl3+eMv9b7P4txGfAInUExjdn3OeKv5b6nc4+LnwAvy57fCFzUs80HgKuzx+uBG0Z5DVfu+a0DtkbH3cAKSSurDqrpJB0OvBW4BiAinouIp3o2q+2+zxl/E6wFfhwRvSPFa7vvewyKv86WAy+TtBx4OYunRl9Hp3AAuAlYK6nf/TL6cnJ/UQDfkLRd0sY+63PdYaoiw2IHeIuk/5H0NUm/N83ghngtMA98QdJ9kj4n6bCebeq87/PED/Xd/wvWA9f1WV7nfd9tUPxQw30fET8D/hl4GNgH7I+Ib/Rs9sK+j4gDwH7g1Xlfw8n9RadHxCl0bux9qaS39qzPdYepigyL/V46p6tvAP4V+M9pB7iE5cApwFURcTLwS2BTzzZ13vd54q/z/ie778K7gK/0W91nWV32PTA0/lrue0mvolOZHw/8FnCYpPf1btbnR3Pveyf3TETszb4/BtxM50bf3Wp7h6lhsUfE0xHxi+zxbcAhko6ceqD9zQFzEXFP9vwmOsmyd5ta7ntyxF/z/Q+douDeiHi0z7o67/sFA+Ov8b5/O/CTiJiPiP8Dvgr8Qc82L+z7rOnmlcATeV/AyR2QdJikVyw8Bt4BPNCz2Tbgwqz3wGl0TqP2TTnURfLELuk1C211kk6l83d/fNqx9hMRjwB7JJ2YLVoL/KBns1rue8gXf533f+a9DG7SqO2+7zIw/hrv+4eB0yS9PItvLfBgzzbbgA3Z4/OAb0Z2dTWPUm7W0UDHADdnn4HlwJcj4nZJfwEQEVfTufnIOcBO4Bng4opi7ZUn9vOAv5R0APhfYP0oH5Ip+BDwpez0ehdwcUP2/YJh8dd2/0t6OXAm8Oddyxqz73PEX8t9HxH3SLqJTrPRAeA+YIukjwGzEbGNzkX6L0raSadiXz/Ka3j6ATOzBLlZxswsQU7uZmYJcnI3M0uQk7uZWYKc3M3MEuTkbmaWICd3M7ME/T8lgZaaMt125AAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['ph'],df['urea'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0ae65e08>"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['ph'],df['osmo'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0aed0888>"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['ph'],df['cond'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0bf0ba48>"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['ph'],df['calc'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note - No relation between ph and other parameters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Plotting osmolarity of Urea solution v/s other parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0bf6e748>"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['osmo'],df['cond'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0bfd3f48>"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['osmo'],df['urea'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0c03e388>"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['osmo'],df['calc'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Findings-** \n",
    "1. Osmolarity is directly proportional to Urea Concentration\n",
    "2. Osmolarity is also linearly related to Conductivity"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Plotting conductivity of urea solution v/s other parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0c0a8188>"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['cond'],df['urea'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0c10f588>"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(df['cond'],df['calc'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note - No relation between conductivity and other reamining parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0xe0c17c1c8>"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# relation between calcium concentration and urea content\n",
    "plt.scatter(df['calc'],df['urea'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "No relation between calcium concentration and urea conteent observed"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Perceptron Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "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>gravity</th>\n",
       "      <th>ph</th>\n",
       "      <th>osmo</th>\n",
       "      <th>cond</th>\n",
       "      <th>urea</th>\n",
       "      <th>calc</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>r</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.015489</td>\n",
       "      <td>6.098667</td>\n",
       "      <td>565.288889</td>\n",
       "      <td>20.557806</td>\n",
       "      <td>237.111111</td>\n",
       "      <td>2.624889</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.021588</td>\n",
       "      <td>5.935588</td>\n",
       "      <td>680.883484</td>\n",
       "      <td>21.355882</td>\n",
       "      <td>305.176471</td>\n",
       "      <td>6.142941</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    gravity        ph        osmo       cond        urea      calc\n",
       "r                                                                 \n",
       "0  1.015489  6.098667  565.288889  20.557806  237.111111  2.624889\n",
       "1  1.021588  5.935588  680.883484  21.355882  305.176471  6.142941"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.groupby('r').mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Train and Test data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df.drop(['r'], axis =1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "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>gravity</th>\n",
       "      <th>ph</th>\n",
       "      <th>osmo</th>\n",
       "      <th>cond</th>\n",
       "      <th>urea</th>\n",
       "      <th>calc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.021</td>\n",
       "      <td>4.91</td>\n",
       "      <td>725.0</td>\n",
       "      <td>20.901282</td>\n",
       "      <td>443</td>\n",
       "      <td>2.45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.017</td>\n",
       "      <td>5.74</td>\n",
       "      <td>577.0</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>296</td>\n",
       "      <td>4.49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.008</td>\n",
       "      <td>7.20</td>\n",
       "      <td>321.0</td>\n",
       "      <td>14.900000</td>\n",
       "      <td>101</td>\n",
       "      <td>2.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.011</td>\n",
       "      <td>5.51</td>\n",
       "      <td>408.0</td>\n",
       "      <td>12.600000</td>\n",
       "      <td>224</td>\n",
       "      <td>2.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1.005</td>\n",
       "      <td>6.52</td>\n",
       "      <td>187.0</td>\n",
       "      <td>7.500000</td>\n",
       "      <td>91</td>\n",
       "      <td>1.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>470</th>\n",
       "      <td>1.025</td>\n",
       "      <td>7.90</td>\n",
       "      <td>721.0</td>\n",
       "      <td>23.600000</td>\n",
       "      <td>301</td>\n",
       "      <td>9.04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>471</th>\n",
       "      <td>1.017</td>\n",
       "      <td>4.81</td>\n",
       "      <td>410.0</td>\n",
       "      <td>13.300000</td>\n",
       "      <td>195</td>\n",
       "      <td>0.58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>472</th>\n",
       "      <td>1.024</td>\n",
       "      <td>5.40</td>\n",
       "      <td>803.0</td>\n",
       "      <td>21.800000</td>\n",
       "      <td>394</td>\n",
       "      <td>7.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>473</th>\n",
       "      <td>1.016</td>\n",
       "      <td>6.81</td>\n",
       "      <td>594.0</td>\n",
       "      <td>21.400000</td>\n",
       "      <td>255</td>\n",
       "      <td>12.20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>474</th>\n",
       "      <td>1.015</td>\n",
       "      <td>6.03</td>\n",
       "      <td>416.0</td>\n",
       "      <td>12.800000</td>\n",
       "      <td>178</td>\n",
       "      <td>9.39</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>474 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     gravity    ph   osmo       cond  urea   calc\n",
       "1      1.021  4.91  725.0  20.901282   443   2.45\n",
       "2      1.017  5.74  577.0  20.000000   296   4.49\n",
       "3      1.008  7.20  321.0  14.900000   101   2.36\n",
       "4      1.011  5.51  408.0  12.600000   224   2.15\n",
       "5      1.005  6.52  187.0   7.500000    91   1.16\n",
       "..       ...   ...    ...        ...   ...    ...\n",
       "470    1.025  7.90  721.0  23.600000   301   9.04\n",
       "471    1.017  4.81  410.0  13.300000   195   0.58\n",
       "472    1.024  5.40  803.0  21.800000   394   7.82\n",
       "473    1.016  6.81  594.0  21.400000   255  12.20\n",
       "474    1.015  6.03  416.0  12.800000   178   9.39\n",
       "\n",
       "[474 rows x 6 columns]"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "Y = df['r']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1      0\n",
       "2      0\n",
       "3      0\n",
       "4      0\n",
       "5      0\n",
       "      ..\n",
       "470    1\n",
       "471    1\n",
       "472    1\n",
       "473    1\n",
       "474    1\n",
       "Name: r, Length: 474, dtype: int64"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train , X_test, Y_train, Y_test = train_test_split(X, Y , test_size = 0.1, stratify = Y, random_state = 1)      # Split ratio = 9:1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "gravity      1.018190\n",
      "ph           6.014390\n",
      "osmo       616.188155\n",
      "cond        20.835934\n",
      "urea       268.556338\n",
      "calc         4.196761\n",
      "dtype: float64 gravity      1.017438\n",
      "ph           6.153542\n",
      "osmo       604.834936\n",
      "cond        21.481250\n",
      "urea       247.312500\n",
      "calc         3.626250\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "print(X_train.mean(),X_test.mean())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    gravity        ph        osmo       cond        urea      calc\n",
      "r                                                                 \n",
      "0  1.015510  6.076008  567.551440  20.564229  240.086420  2.674198\n",
      "1  1.021749  5.932568  680.771332  21.196721  306.360656  6.218525\n"
     ]
    }
   ],
   "source": [
    "print(X_train.groupby(Y_train).mean())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(426,) (48,)\n"
     ]
    }
   ],
   "source": [
    "print(Y_train.shape, Y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(X_train.T, '*')\n",
    "plt.xticks(rotation = 'vertical')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Converting into numpy array \n",
    "X_train_mod = X_train.values\n",
    "X_test_mod = X_test.values\n",
    "Y_train_mod = Y_train.values\n",
    "Y_test_mod = Y_test.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(426, 6)"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_mod.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "class Perceptron:\n",
    "    def __init__ (self):\n",
    "        self.w = None\n",
    "        self.b = None\n",
    "        \n",
    "    def model(self, x):\n",
    "        return 1 if (np.dot(self.w,x) >= self.b) else 0\n",
    "    \n",
    "    def predict(self, X):\n",
    "        Y = []\n",
    "        for x in X:\n",
    "            result = self.model(x)\n",
    "            Y.append(result)\n",
    "        return np.array(Y)\n",
    "    \n",
    "    def fit(self, X, Y, epochs = 1, lr = 1):\n",
    "        self.w = np.zeros(X.shape[1])\n",
    "        self.b = 0\n",
    "    \n",
    "        accuracy = {}\n",
    "        max_accuracy = 0\n",
    "    \n",
    "        wt_matrix = []\n",
    "        \n",
    "        for i in range(epochs):\n",
    "            for x, y in zip(X, Y):\n",
    "                y_pred = self.model(x)\n",
    "                if y == 1 and y_pred == 0:\n",
    "                    self.w = self.w + lr * x\n",
    "                    self.b = self.b - lr * 1\n",
    "                elif y == 0 and y_pred == 1:\n",
    "                    self.w = self.w - lr * x\n",
    "                    self.b = self.b + lr * 1\n",
    "            wt_matrix.append(self.w)\n",
    "            accuracy[i] = accuracy_score(self.predict(X), Y)\n",
    "            if (accuracy[i] > max_accuracy):\n",
    "                max_accuracy = accuracy[i]\n",
    "                chkptw = self.w\n",
    "                chkptb = self.b\n",
    "        \n",
    "        self.w = chkptw\n",
    "        self.b = chkptb\n",
    "        \n",
    "        acc = list(accuracy.values())\n",
    "        \n",
    "        plt.plot(acc)\n",
    "        plt.ylim([0, 1])\n",
    "        plt.show()\n",
    "        \n",
    "        print(max_accuracy)\n",
    "        \n",
    "        return np.array(wt_matrix)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Key** \n",
    "1. learning rate = lr.      \n",
    "In machine learning and statistics, the learning rate is a tuning parameter in an optimization algorithm that determines the step size at each iteration while moving toward a minimum of a loss function.\n",
    "2. chkptw and chktb are check pointers. Checkpointing is a mechanism to store the state of a computation so that it can be retrieved at a later point in time and continued.\n",
    "3. epochs - An epoch is a term used in machine learning and indicates the number of passes through the entire training dataset the machine learning algorithm has completed."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "perceptron = Perceptron()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8215962441314554\n"
     ]
    }
   ],
   "source": [
    "wt_matrix = perceptron.fit(X_train_mod, Y_train_mod,500,0.1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8333333333333334\n"
     ]
    }
   ],
   "source": [
    "Y_pred_test = perceptron.predict(X_test_mod)\n",
    "print(accuracy_score(Y_pred_test, Y_test_mod))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[-1.47070000e+00 -9.25800000e+00  4.62076923e+01 -1.89105128e+01\n",
      "   5.59000000e+01  2.37600000e+01]\n",
      " [-3.14560000e+00 -2.04000000e+01  3.84115385e+01 -3.73710256e+01\n",
      "   6.42000000e+01  4.68790000e+01]\n",
      " [-4.91670000e+00 -3.19690000e+01  3.68192308e+01 -5.86715385e+01\n",
      "   7.01000000e+01  7.04650000e+01]\n",
      " ...\n",
      " [-1.84168500e+02 -1.36854800e+03  3.04692308e+02 -4.43959385e+03\n",
      "  -2.55800000e+02  6.51792300e+03]\n",
      " [-1.84256400e+02 -1.36977200e+03  2.23803846e+02 -4.44622397e+03\n",
      "  -2.95000000e+02  6.52406500e+03]\n",
      " [-1.84642400e+02 -1.37260500e+03  2.92615385e+02 -4.45046410e+03\n",
      "  -2.21800000e+02  6.52951700e+03]]\n"
     ]
    }
   ],
   "source": [
    "print(wt_matrix)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(wt_matrix[-1,:])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Findings"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1. Learning rate for Perceptron Model is not necessary.\n",
    "2. The model is approximately 83% accurate which is quite less when when compared to more advanced learning models. \n",
    "3. Epochs and Learning Rate are hyperparameters that can be configured using advance mathematics but here trial and error has been used. It is done so for learning purpose."
   ]
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}