isotopes_regression_answer.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "CALCULATE A REGRESSION LINE TO PREDICT THE \n",
    "OXYGEN-18 ISOTOPE  , Delta_18O, VERSUS THE DEUTERIUM, Delta_D, ONE OF THE TWO ISOTOPES OF \n",
    "HYDROGEN .\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import dependencies\n",
    "import pandas as pd\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "\n",
    "from sklearn.datasets import make_regression\n",
    "from sklearn.linear_model import LinearRegression\n",
    "%matplotlib inline\n",
    "# Hide warning messages in notebook\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>TIMESTAMP</th>\n",
       "      <th>Delta_18O</th>\n",
       "      <th>Delta_D</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "      <th>Landscape</th>\n",
       "      <th>Country</th>\n",
       "      <th>Name</th>\n",
       "      <th>sLatitude</th>\n",
       "      <th>sLongitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>201306181500</td>\n",
       "      <td>-13.640750</td>\n",
       "      <td>-126.381000</td>\n",
       "      <td>28.3N</td>\n",
       "      <td>16.5W</td>\n",
       "      <td>Mountain</td>\n",
       "      <td>SP</td>\n",
       "      <td>Teide</td>\n",
       "      <td>28.3</td>\n",
       "      <td>-16.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>201306181600</td>\n",
       "      <td>-15.774167</td>\n",
       "      <td>-145.946000</td>\n",
       "      <td>28.3N</td>\n",
       "      <td>16.5W</td>\n",
       "      <td>Mountain</td>\n",
       "      <td>SP</td>\n",
       "      <td>Teide</td>\n",
       "      <td>28.3</td>\n",
       "      <td>-16.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>201306181700</td>\n",
       "      <td>-20.673000</td>\n",
       "      <td>-182.658333</td>\n",
       "      <td>28.3N</td>\n",
       "      <td>16.5W</td>\n",
       "      <td>Mountain</td>\n",
       "      <td>SP</td>\n",
       "      <td>Teide</td>\n",
       "      <td>28.3</td>\n",
       "      <td>-16.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>201306181800</td>\n",
       "      <td>-25.917500</td>\n",
       "      <td>-223.841500</td>\n",
       "      <td>28.3N</td>\n",
       "      <td>16.5W</td>\n",
       "      <td>Mountain</td>\n",
       "      <td>SP</td>\n",
       "      <td>Teide</td>\n",
       "      <td>28.3</td>\n",
       "      <td>-16.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>201306181900</td>\n",
       "      <td>-26.898667</td>\n",
       "      <td>-231.194333</td>\n",
       "      <td>28.3N</td>\n",
       "      <td>16.5W</td>\n",
       "      <td>Mountain</td>\n",
       "      <td>SP</td>\n",
       "      <td>Teide</td>\n",
       "      <td>28.3</td>\n",
       "      <td>-16.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      TIMESTAMP  Delta_18O     Delta_D Latitude Longitude Landscape Country  \\\n",
       "0  201306181500 -13.640750 -126.381000    28.3N     16.5W  Mountain      SP   \n",
       "1  201306181600 -15.774167 -145.946000    28.3N     16.5W  Mountain      SP   \n",
       "2  201306181700 -20.673000 -182.658333    28.3N     16.5W  Mountain      SP   \n",
       "3  201306181800 -25.917500 -223.841500    28.3N     16.5W  Mountain      SP   \n",
       "4  201306181900 -26.898667 -231.194333    28.3N     16.5W  Mountain      SP   \n",
       "\n",
       "    Name  sLatitude  sLongitude  \n",
       "0  Teide       28.3       -16.5  \n",
       "1  Teide       28.3       -16.5  \n",
       "2  Teide       28.3       -16.5  \n",
       "3  Teide       28.3       -16.5  \n",
       "4  Teide       28.3       -16.5  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Read the csv file into a pandas DataFrame\n",
    "mega_df=pd.read_csv('./mega.csv', index_col = 0)\n",
    "\n",
    "mega_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape:  (138365, 1) (138365, 1)\n"
     ]
    }
   ],
   "source": [
    "\"\"\" Quantifying Linear Regression\n",
    " Relationship between Delta_18O and Delta_D\n",
    " Assign the data to X and y \n",
    "Note: Sklearn requires a two-dimensional array of values\"\"\"\n",
    "\n",
    "X = mega_df[\"Delta_18O\"].values.reshape(-1, 1)\n",
    "\n",
    "y = mega_df[\"Delta_D\"].values.reshape(-1, 1)\n",
    "\n",
    "print(\"Shape: \", X.shape, y.shape)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "A linear trend exist between Delta_18O and Delta_D water\n"
     ]
    },
    {
     "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": [
    "# Scatter plot the data to see if a linear trend exists\n",
    "\n",
    "plt.scatter(X, y)\n",
    "\n",
    "plt.xlabel(\"Delta_18O\")\n",
    "plt.ylabel(\"Delta_D\")\n",
    "plt.title(\"Relationship between Delta_18O and Delta_D \")\n",
    "\n",
    "print(\"A linear trend exist between Delta_18O and Delta_D water\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "mega_df=mega_df.head(500)\n",
    "X = mega_df[\"Delta_18O\"].values.reshape(-1, 1)\n",
    "y = mega_df[\"Delta_D\"].values.reshape(-1, 1)\n",
    "from sklearn.linear_model import LinearRegression\n",
    "model = LinearRegression()\n",
    "# Use sklearn's `train_test_split` to split the data into training and testing\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean Squared Error (MSE): 128.09062293227183\n",
      "R-squared (R2 ): 0.9801120413258104\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.9801120413258104"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Train the model using the training data\n",
    "model.fit(X_train, y_train)\n",
    "\n",
    "\n",
    "# Use our model to make Hydrogen Isotope Prediction\n",
    "predicted = model.predict(X_test)\n",
    "\n",
    "\"\"\" \n",
    "Score the predictions with mse and r2\n",
    "Calculate the mean_squared_error and the r-squared value\n",
    " for the testing data \"\"\"\n",
    "\n",
    "from sklearn.metrics import mean_squared_error, r2_score\n",
    "\n",
    "mse = mean_squared_error(y_test, predicted)\n",
    "\n",
    "r2 = r2_score(y_test, predicted)\n",
    "\n",
    "print(f\"Mean Squared Error (MSE): {mse}\")\n",
    "print(f\"R-squared (R2 ): {r2}\")\n",
    "\n",
    "#And score the model using the unseen testing data\n",
    "model.score(X_test, y_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Global  Water Line shows that the water isotope \n",
      "      values do not converge along a single straight line. \n",
      "      There are some branches that diverge from the main fitted line.\n",
      "      This phenomenon suggests that different  water lines prevail in different regions. \n"
     ]
    },
    {
     "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": [
    "\"\"\"We can view the coefficients and intercept of the line from the coef_ and intercept_ attributes.\n",
    "#Note that the _ suffix indicates that the attribute is available after model is fit to the data (trained).\"\"\"\n",
    "\n",
    "a=model.coef_\n",
    "b=model.intercept_\n",
    "y_predict = a*X_train + b\n",
    "\n",
    "plt.scatter(X_train,y_train)\n",
    "plt.plot(X_train, y_predict, color=\"r\")\n",
    "\n",
    "plt.xlabel(\"Delta_18O\")\n",
    "plt.ylabel(\"Delta_D\")\n",
    "plt.title(\"Asymetric relationship between Delta_18O and Delta_D \")\n",
    "print(\"\"\"The Global  Water Line shows that the water isotope \n",
    "      values do not converge along a single straight line. \n",
    "      There are some branches that diverge from the main fitted line.\n",
    "      This phenomenon suggests that different  water lines prevail in different regions. \"\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "error=predicted - y_test\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>Predicted</th>\n",
       "      <th>Actual</th>\n",
       "      <th>Error</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-196.890568</td>\n",
       "      <td>-194.380667</td>\n",
       "      <td>-2.509901</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-296.756791</td>\n",
       "      <td>-284.163667</td>\n",
       "      <td>-12.593124</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-149.758155</td>\n",
       "      <td>-147.041500</td>\n",
       "      <td>-2.716655</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-141.915232</td>\n",
       "      <td>-140.571500</td>\n",
       "      <td>-1.343732</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-284.322124</td>\n",
       "      <td>-280.853333</td>\n",
       "      <td>-3.468791</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Predicted      Actual      Error\n",
       "0 -196.890568 -194.380667  -2.509901\n",
       "1 -296.756791 -284.163667 -12.593124\n",
       "2 -149.758155 -147.041500  -2.716655\n",
       "3 -141.915232 -140.571500  -1.343732\n",
       "4 -284.322124 -280.853333  -3.468791"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df =pd.DataFrame({\"Predicted\": predicted.reshape(-1,), \"Actual\": y_test.reshape(-1,), \"Error\": error.reshape(-1,)})\n",
    "df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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": [
    "# Make predictions using a fitted model\n",
    "# Plot the difference between the model predicted values and actual y values, versus the model predicted values\n",
    "# Hint: You can predict values of X training and testing data using the model.predict() method on a fitted model\n",
    "\n",
    "### BEGIN SOLUTION\n",
    "#predictions = model.predict(X_test_scaled)\n",
    "#model.fit(X_train_scaled, y_train_scaled)\n",
    "plt.scatter(model.predict(X_train), model.predict(X_train) - y_train, c=\"blue\", label=\"Training Data\")\n",
    "plt.scatter(model.predict(X_test), model.predict(X_test) - y_test, c=\"red\", label=\"Testing Data\")\n",
    "plt.legend()\n",
    "plt.hlines(y=0, xmin=y_test.min(), xmax=y_test.max())\n",
    "plt.title(\"Residual Plot\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.7.4 64-bit ('base': conda)",
   "language": "python",
   "name": "python37464bitbaseconda8399b2a7c3c9404799aa7ca3ec89ee5a"
  },
  "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": 2
}