Machine Learning - Ground Water Survey.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Machine Learning: Ground Water Survey"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This report is a part of **Machine Learning For All** Slack group. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Source of data: http://college.cengage.com/mathematics/brase/understandable_statistics/8e/students/datasets/slr/slr09.html"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Importing Necessary Libraries  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sbs\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Reading Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_org=pd.read_csv('slr09.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exploring our data. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "X = pH of well water,\n",
    "Y = Bicarbonate (parts per million) of well water"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>X</th>\n",
       "      <th>Y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7.6</td>\n",
       "      <td>157</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7.1</td>\n",
       "      <td>174</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.2</td>\n",
       "      <td>175</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7.5</td>\n",
       "      <td>188</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.4</td>\n",
       "      <td>171</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     X    Y\n",
       "0  7.6  157\n",
       "1  7.1  174\n",
       "2  8.2  175\n",
       "3  7.5  188\n",
       "4  7.4  171"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_org.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Spliting our data for training and testing"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Separating out pH and Bicarbonate values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "ph=data_org.iloc[:,:-1].values\n",
    "bicarb=data_org.iloc[:,1].values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plot of Original Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x7a6bfb0>"
      ]
     },
     "execution_count": 5,
     "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(ph,bicarb)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Using Linear Regression to fit line through our data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\scipy\\stats\\stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.\n",
      "  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x7ccf8d0>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 360x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sbs.lmplot(\"X\",\"Y\",data_org)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We will be using 30% of our data for testing and 70% for training. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "ph_train,ph_test,bicarb_train,bicarb_test=train_test_split(ph,bicarb,test_size=0.3,random_state=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Training our model. We will be using Linear Regression model from scikit-learn library. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Training will be done with our **ph_train** & **bicarb_train** training sets."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**ph_test** & **bicarb_test** will be kept aside for testing our model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None,\n",
       "         normalize=False)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "lr=LinearRegression()\n",
    "lr.fit(ph_train,bicarb_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now lets use our model ***lr*** to predict Bicarbonate values. Our model ***lr*** haven't seen these **ph_test** values. We had kept it aside in the beginning for testing purpose."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[7.2],\n",
       "       [7.9],\n",
       "       [8.2],\n",
       "       [8. ],\n",
       "       [7.8],\n",
       "       [7.5],\n",
       "       [7.3],\n",
       "       [7.3],\n",
       "       [8.5],\n",
       "       [7.8],\n",
       "       [7.1]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ph_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "prediction=lr.predict(ph_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([155.09994459, 134.41944868, 125.556379  , 131.46509212,\n",
       "       137.37380524, 146.23687491, 152.14558803, 152.14558803,\n",
       "       116.69330932, 137.37380524, 158.05430115])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prediction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Below is our original values of Bicarbonate."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([133,  53, 175, 190, 143, 188, 262, 121,  48, 105, 174], dtype=int64)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bicarb_test[:]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Conclusion:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\scipy\\stats\\stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.\n",
      "  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x89d8b70>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 360x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sbs.lmplot(\"X\",\"Y\",data_org)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As you can see our learning model tried its best to fit a line through the data. But due to scattered values and less training data it is quite inefficient."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([155.09994459])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.predict([[7.2]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([116.69330932])"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr.predict([[8.5]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}