{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Coursework 1 - Tutorial (25 October 2019)\n",
"Notebook prepared by your tutor MichaĆ Robert Hoffman - M.R.Hoffman@soton.ac.uk\n",
"\n",
"Feel free to modify as required.\n",
"\n",
"## Overview\n",
"\n",
"In this coursework, we use Python to import fishing data and analyse it.\n",
"Please read the coursework specification (CW1) for further instructions.\n",
"\n",
"This tutorial will cover the most important elements you need to report on, but not all! Always refer to your lecture notes if you're not sure what to cover.\n",
"\n",
"### Important notes:\n",
"\n",
"You are required to submit a properly formatted report. Jupyter notebook submissions will not be accepted! Also the graphics we generate below are very basic. You will be required to make them look more professional, by manipulating the size of the graphics, and finding optimal graphing parameters, such as bin sizes etc. You may not reuse your friends image files, as that may constitute a breach of academic integrity. Also, all your write-ups in the final report must be your own original work.\n",
"\n",
"Please also note that some outputs have been pre-populated from you. When you change your code cells and run them, the outputs may change slightly, which is expected! If your new output looks very different to the previous outputs, that could be a problem."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Importing the libraries\n",
"\n",
"In this case we are going to use the library pandas. \n",
"You can find the documentation of the library [here](https://pandas.pydata.org/). \n",
"This library is one of the most important libraries to analyse data in Python. \n",
"It is connected with Numpy and Matplotlib libraries. Check more about these libraries [here]\n",
"(http://www.numpy.org/) and [here](https://matplotlib.org/).\n",
"\n",
"Fill in the blanks in the imports below:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# Import the libraries pandas, and matplotlib\n",
"# for matplotlib just load pyplot\n",
"import _ _ _ as pd\n",
"import _ _ _.pyplot as plt #This is to format your plots and do things like plt.figure(figsize=(20,10))\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Everytime you change the code, remember to press \"Run\" or press Ctrl+Enter (or Shift+Enter) to rerun your code.\n",
"\n",
"In the next section, we fill in the filename (file is specified in your coursework spec, download it first and place in a directory that can be accessed by your Jupyter Notebook) and read in the data.\n",
"\n",
"## Reading the file into a dataframe.\n",
"\n",
"(NB. Do you know what a dataframe is? Can you explain it using simple English?)\n",
"\n",
"For more information on dataframes, google \"what are pandas dataframes?\".\n",
"\n",
"You'll need to pass some paramateres to the pandas library, so that it knows the following:\n",
"the filename,\n",
"the separator (what character separates the data points in each row in the file?)\n",
"is there a header in the file (if not, say None)\n",
"is there a special column in the file that's used to index that file?"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"filename = _ _ _\n",
"\n",
"time_weight_bait_data = pd.read_csv(_ _ _,sep= _ _ _,header=_ _ _ ,index_col=_ _ _)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Find a way of finding the \"shape\" of the data. You can google this if necessary.\n",
"Shape is a tuple that gives you the number of columns followed by the number of rows.\n",
"Is shape a method or an attribute? What does it mean? What's the difference?\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(400, 3)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"time_weight_bait_data._ _ _"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"#Give human-readable names to the columns\n",
"___.columns=[\".....\",\".....\",\".....\"]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" Time \n",
" Weight \n",
" Bait \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 15.25 \n",
" 2.40 \n",
" B \n",
" \n",
" \n",
" 1 \n",
" 7.43 \n",
" 1.66 \n",
" C \n",
" \n",
" \n",
" 2 \n",
" 7.17 \n",
" 2.75 \n",
" C \n",
" \n",
" \n",
" 3 \n",
" 2.93 \n",
" 1.21 \n",
" A \n",
" \n",
" \n",
" 4 \n",
" 11.07 \n",
" 0.39 \n",
" C \n",
" \n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Time Weight Bait\n",
"0 15.25 2.40 B\n",
"1 7.43 1.66 C\n",
"2 7.17 2.75 C\n",
"3 2.93 1.21 A\n",
"4 11.07 0.39 C"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Display only the top rows\n",
"___.___()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Now, you will display a sample of 10 random rows\n",
"___._____(___)\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[,\n",
" ]],\n",
" dtype=object)"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Now, generate histograms for each column using the DataFrame's built-in function\n",
"# N.B. there are many ways to do this\n",
"# First, type a dot \".\" after the objects name\n",
"# Next press the Tab key \n",
"# Type \"h\" and you will see the methods starting with that letter\n",
"# Remember to add the brackets () at the end for a function call!\n",
"\n",
"time_weight_bait_data\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Now specify the column size Weight (if you named it that!), hide the grid, and set bins to 50\n",
"#Then rerun the histogram"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[]],\n",
" dtype=object)"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEICAYAAABYoZ8gAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAE7NJREFUeJzt3X+sX/V93/Hna4RkHbAGyi1xAMddw1hpNEh0Z9qFIPID1xAU0ilLsbqUdqROIiIlaqSIbFpJk02imppOLV2RF1zIRkm6EVpWIMFKUQwdAa6pSfgRikNdYeNgJ074sUSLnL73xz1WLzffr/3193x9v/b9PB/SV99zPufzPed9ruF1zz3f8zknVYUkqR3/YNoFSJKWlsEvSY0x+CWpMQa/JDXG4Jekxhj8ktQYg18aQZLrkvyHEfvekOQ/Hu6apHEZ/Fq2knwsyZ2L2p4c0nbZgdZVVe+vqk9OqK5K8tpJrEsah8Gv5Wwz8C+THAOQZAVwLPD6RW2v7fpKTTD4tZw9yHzQn9PNvwm4G3hiUds3quqZJP8syaYke5M8keTd+1e0+PRNko8m2ZXkmSTvHXAUf2KS25O8kOT+JD/dfW7/L5iHk7yY5JcOz65Lwxn8Wraq6gfA/cD5XdP5wD3AvYvaNic5DtgE/DHwk8BlwH9Nctbi9SZZC/wG8Dbm/1q4YMDmLwN+CzgR2Ab8p66m/ds9u6qOr6rP9dtL6dAZ/Fruvszfh/ybmA/+exa1fRm4BNheVX9UVfuq6q+AW4B/PWCd7wb+qKoerarvAR8f0OfWqnqgqvYBN/H3f2FIU2fwa7nbDJyX5CRgpqqeBP4P8+f+TwJe1/V5DXBuku/ufwG/DLxqwDpfDTy9YP7pAX2+uWD6e8Dx/XdFmoyXTbsA6TC7D/hx4NeBvwSoqueTPNO1PVNVf5PkaeDLVXXhCOvcBZy2YP70CdcsHVYe8WtZq6rvA3PMn5O/Z8Gie7u2/V+2/jnwT5O8J8mx3etfJPmZAav9E+DXkvxMkn8EjHR9/wLPAv/kED8jTYzBrxZ8mfkvbO9d0HZP17YZoKpeANYw/6XsM8yfqvlt4BWLV1ZVdwK/x/wVQtuAr3SL/t+I9XwcuLE7pfTug3WWJi0+iEXqp/ur4BHgFd2XudIRzSN+aQxJfjHJK5KcyPxfBv/b0NfRwuCXxvM+YDfwDeCHwAemW440Ok/1SFJjPOKXpMYckdfxn3zyybVq1applyFJR40tW7Z8q6pmRul7RAb/qlWrmJubm3YZknTUSPK3o/b1VI8kNcbgl6TGGPyS1BiDX5IaY/BLUmMMfklqzEGDP8npSe5O8liSR5N8qGs/qXs+6ZPd+4lDPn951+fJJJdPegckSYdmlCP+fcBHquos4OeAK7vnkF4FfKmqzgC+1M2/RPeEo6uBc4HVwNXDfkFIkpbGQYO/qnZV1UPd9AvA48CpwKXAjV23G4F3Dvj4LwCbqmpvVX2H+YdZr51E4ZKk8RzSyN0kq4DXA/cDp1TVrm7RN4FTBnzkVF76PNIdXdugda8H1gOsXLnyUMoayaqrbh/Yvv2at098W0fCdiVpmJG/3E1yPHAL8OGqen7hspq/xWev23xW1Yaqmq2q2ZmZkW43IUkaw0jBn+RY5kP/pqr6fNf8bJIV3fIVzN+bfLGdvPRB1Kd1bZKkKRnlqp4A1wOPV9WnFiy6Ddh/lc7lwJ8N+PgXgTVJTuy+1F3TtUmSpmSUI/43Au8B3pJka/e6GLgGuDDJk8DbunmSzCb5NEBV7QU+CTzYvT7RtUmSpuSgX+5W1b1Ahix+64D+c8B7F8xvBDaOW6AkabIcuStJjTH4JakxBr8kNcbgl6TGHJHP3JVg+KhncOSz1IdH/JLUGINfkhpj8EtSYwx+SWqMwS9JjTH4JakxBr8kNcbgl6TGGPyS1BiDX5IaY/BLUmMOeq+eJBuBS4DdVfW6ru1zwJldl1cC362qcwZ8djvwAvBDYF9VzU6obknSmEa5SdsNwLXAZ/Y3VNUv7Z9O8jvAcwf4/Jur6lvjFihJmqxRHr24OcmqQcu6B7G/G3jLZMuSJB0ufc/xvwl4tqqeHLK8gLuSbEmyvue2JEkT0Pd+/OuAmw+w/Lyq2pnkJ4FNSb5eVZsHdex+MawHWLlyZc+yJEnDjH3En+RlwL8CPjesT1Xt7N53A7cCqw/Qd0NVzVbV7MzMzLhlSZIOos+pnrcBX6+qHYMWJjkuyQn7p4E1wCM9tidJmoCDBn+Sm4H7gDOT7EhyRbfoMhad5kny6iR3dLOnAPcmeRh4ALi9qr4wudIlSeMY5aqedUPaf3VA2zPAxd30U8DZPeuTJE2YD1uXpmDYg+R9iLyWgrdskKTGGPyS1BiDX5IaY/BLUmMMfklqjMEvSY0x+CWpMQa/JDXG4Jekxhj8ktQYg1+SGmPwS1JjDH5JaozBL0mNMfglqTEGvyQ1ZpRHL25MsjvJIwvaPp5kZ5Kt3eviIZ9dm+SJJNuSXDXJwiVJ4xnliP8GYO2A9t+tqnO61x2LFyY5BvgD4CLgLGBdkrP6FCtJ6u+gwV9Vm4G9Y6x7NbCtqp6qqh8AnwUuHWM9kqQJ6vPM3Q8m+RVgDvhIVX1n0fJTgacXzO8Azh22siTrgfUAK1eu7FGWjjbDnj87zmd8Zq10cON+ufuHwE8D5wC7gN/pW0hVbaiq2aqanZmZ6bs6SdIQYwV/VT1bVT+sqr8D/hvzp3UW2wmcvmD+tK5NkjRFYwV/khULZn8ReGRAtweBM5L8VJKXA5cBt42zPUnS5Bz0HH+Sm4ELgJOT7ACuBi5Icg5QwHbgfV3fVwOfrqqLq2pfkg8CXwSOATZW1aOHZS8kSSM7aPBX1boBzdcP6fsMcPGC+TuAH7nUU5I0PY7claTGGPyS1BiDX5IaY/BLUmMMfklqTJ9bNiwL0xr67y0HJE2LR/yS1BiDX5IaY/BLUmMMfklqjMEvSY0x+CWpMQa/JDXG4Jekxhj8ktSY5kfuHk2OtNG+h/qQ9GmOSj7Un92R9rOWJskjfklqzEGDP8nGJLuTPLKg7T8n+XqSrya5Nckrh3x2e5KvJdmaZG6ShUuSxjPKEf8NwNpFbZuA11XVPwf+GvjYAT7/5qo6p6pmxytRkjRJBw3+qtoM7F3UdldV7etmvwKcdhhqkyQdBpM4x/9vgTuHLCvgriRbkqw/0EqSrE8yl2Ruz549EyhLkjRIr+BP8u+BfcBNQ7qcV1VvAC4Crkxy/rB1VdWGqpqtqtmZmZk+ZUmSDmDs4E/yq8AlwC9XVQ3qU1U7u/fdwK3A6nG3J0majLGCP8la4KPAO6rqe0P6HJfkhP3TwBrgkUF9JUlLZ5TLOW8G7gPOTLIjyRXAtcAJwKbuUs3rur6vTnJH99FTgHuTPAw8ANxeVV84LHshSRrZQUfuVtW6Ac3XD+n7DHBxN/0UcHav6iRJE+ctGw6RQ/l1OPnfl5aCt2yQpMYY/JLUGINfkhpj8EtSYwx+SWqMwS9JjTH4JakxBr8kNcbgl6TGOHL3CHOoDzA/0Gd8kPj0jfPvKR1uHvFLUmMMfklqjMEvSY0x+CWpMQa/JDXG4JekxowU/Ek2Jtmd5JEFbScl2ZTkye79xCGfvbzr82SSyydVuCRpPKMe8d8ArF3UdhXwpao6A/hSN/8SSU4CrgbOBVYDVw/7BSFJWhojBX9VbQb2Lmq+FLixm74ReOeAj/4CsKmq9lbVd4BN/OgvEEnSEuozcveUqtrVTX8TOGVAn1OBpxfM7+jafkSS9cB6gJUrV45d1LRGSjpCsw3+O2s5mMiXu1VVQPVcx4aqmq2q2ZmZmUmUJUkaoE/wP5tkBUD3vntAn53A6QvmT+vaJElT0if4bwP2X6VzOfBnA/p8EViT5MTuS901XZskaUpGvZzzZuA+4MwkO5JcAVwDXJjkSeBt3TxJZpN8GqCq9gKfBB7sXp/o2iRJUzLSl7tVtW7IorcO6DsHvHfB/EZg41jVSZImzpG7ktQYg1+SGmPwS1JjDH5JaozBL0mN8WHrQ7Q4NP9wP4S9xZ+pdCTyiF+SGmPwS1JjDH5JaozBL0mNMfglqTEGvyQ1xuCXpMYY/JLUGINfkhrjyN1lbFIjZZfziNvlvG/SMB7xS1Jjxg7+JGcm2brg9XySDy/qc0GS5xb0+c3+JUuS+hj7VE9VPQGcA5DkGGAncOuArvdU1SXjbkeSNFmTOtXzVuAbVfW3E1qfJOkwmVTwXwbcPGTZzyd5OMmdSX522AqSrE8yl2Ruz549EypLkrRY7+BP8nLgHcD/HLD4IeA1VXU28PvAnw5bT1VtqKrZqpqdmZnpW5YkaYhJHPFfBDxUVc8uXlBVz1fVi930HcCxSU6ewDYlSWOaRPCvY8hpniSvSpJuenW3vW9PYJuSpDH1GsCV5DjgQuB9C9reD1BV1wHvAj6QZB/wfeCyqqo+25Qk9dMr+Kvq/wI/sajtugXT1wLX9tmGdCgciSsdnCN3JakxBr8kNcbgl6TGGPyS1BiDX5IaY/BLUmMMfklqjMEvSY0x+CWpMQa/JDXGh61LR4Fht6LYfs3bl7gSDXK0/ft4xC9JjTH4JakxBr8kNcbgl6TGGPyS1BiDX5Ia0zv4k2xP8rUkW5PMDVieJL+XZFuSryZ5Q99tSpLGN6nr+N9cVd8asuwi4IzudS7wh927JGkKluJUz6XAZ2reV4BXJlmxBNuVJA0wieAv4K4kW5KsH7D8VODpBfM7uraXSLI+yVySuT179kygLEnSIJMI/vOq6g3Mn9K5Msn546ykqjZU1WxVzc7MzEygLEnSIL2Dv6p2du+7gVuB1Yu67AROXzB/WtcmSZqCXsGf5LgkJ+yfBtYAjyzqdhvwK93VPT8HPFdVu/psV5I0vr5X9ZwC3Jpk/7r+uKq+kOT9AFV1HXAHcDGwDfge8Gs9tylJ6qFX8FfVU8DZA9qvWzBdwJV9tiNJmhxH7kpSYwx+SWqMwS9JjTH4JakxBr8kNcbgl6TGGPyS1BiDX5IaY/BLUmMMfklqjMEvSY0x+CWpMQa/JDXG4Jekxhj8ktSYvg9ikdSoVVfdPrB9+zVvX+JKJm857xt4xC9JzRk7+JOcnuTuJI8leTTJhwb0uSDJc0m2dq/f7FeuJKmvPqd69gEfqaqHugeub0myqaoeW9Tvnqq6pMd2JEkTNPYRf1XtqqqHuukXgMeBUydVmCTp8JjIOf4kq4DXA/cPWPzzSR5OcmeSnz3AOtYnmUsyt2fPnkmUJUkaoHfwJzkeuAX4cFU9v2jxQ8Brqups4PeBPx22nqraUFWzVTU7MzPTtyxJ0hC9gj/JscyH/k1V9fnFy6vq+ap6sZu+Azg2ycl9tilJ6qfPVT0Brgcer6pPDenzqq4fSVZ32/v2uNuUJPXX56qeNwLvAb6WZGvX9u+AlQBVdR3wLuADSfYB3wcuq6rqsU1JUk9jB39V3QvkIH2uBa4ddxuSxne0jz4dVv8wB9qvaf0sJrkPk+TIXUlqjMEvSY0x+CWpMQa/JDXG4Jekxhj8ktQYg1+SGmPwS1JjDH5JaozP3JWOYoc6MnQpHOoo2Untw1L8LI7En/c4POKXpMYY/JLUGINfkhpj8EtSYwx+SWqMwS9JjTH4JakxfR+2vjbJE0m2JblqwPJXJPlct/z+JKv6bE+S1F+fh60fA/wBcBFwFrAuyVmLul0BfKeqXgv8LvDb425PkjQZfY74VwPbquqpqvoB8Fng0kV9LgVu7Kb/F/DWJAd8Tq8k6fDqc8uGU4GnF8zvAM4d1qeq9iV5DvgJ4FuLV5ZkPbC+m30xyRNj1HTyoHU3otV9b3W/Ycx9z5T+7p7gdif2bz6tn8UwI9RzoH1/zajbOWLu1VNVG4ANfdaRZK6qZidU0lGl1X1vdb+h3X1vdb9hcvve51TPTuD0BfOndW0D+yR5GfDjwLd7bFOS1FOf4H8QOCPJTyV5OXAZcNuiPrcBl3fT7wL+oqqqxzYlST2NfaqnO2f/QeCLwDHAxqp6NMkngLmqug24HvjvSbYBe5n/5XA49TpVdJRrdd9b3W9od99b3W+Y0L7HA3BJaosjdyWpMQa/JDVm2QT/wW4fsVwl2Zhkd5JHpl3LUkpyepK7kzyW5NEkH5p2TUshyT9M8kCSh7v9/q1p17SUkhyT5K+S/Pm0a1lKSbYn+VqSrUnmeq9vOZzj724f8dfAhcwPJHsQWFdVj021sCWQ5HzgReAzVfW6adezVJKsAFZU1UNJTgC2AO9c7v/m3cj346rqxSTHAvcCH6qqr0y5tCWR5DeAWeAfV9Ul065nqSTZDsxW1UQGri2XI/5Rbh+xLFXVZuavmGpKVe2qqoe66ReAx5kfKb6s1bwXu9lju9fRf/Q2giSnAW8HPj3tWo52yyX4B90+YtmHgOZ1d319PXD/dCtZGt3pjq3AbmBTVTWx38B/AT4K/N20C5mCAu5KsqW7vU0vyyX41agkxwO3AB+uquenXc9SqKofVtU5zI+WX51k2Z/iS3IJsLuqtky7lik5r6rewPzdkK/sTvGObbkE/yi3j9Ay053jvgW4qao+P+16llpVfRe4G1g77VqWwBuBd3Tnuj8LvCXJ/5huSUunqnZ277uBW5k/vT225RL8o9w+QstI9yXn9cDjVfWpadezVJLMJHllN/1jzF/Q8PXpVnX4VdXHquq0qlrF/P/ff1FV/2bKZS2JJMd1FzCQ5DhgDdDrKr5lEfxVtQ/Yf/uIx4E/qapHp1vV0khyM3AfcGaSHUmumHZNS+SNwHuYP/Lb2r0unnZRS2AFcHeSrzJ/wLOpqpq6tLFBpwD3JnkYeAC4vaq+0GeFy+JyTknS6JbFEb8kaXQGvyQ1xuCXpMYY/JLUGINfkhpj8EtSYwx+SWrM/wd3q5gmsa7atQAAAABJRU5ErkJggg==\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"time_weight_bait_data.___(column=\"___\",grid=_,bins=_)\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" Time \n",
" Weight \n",
" \n",
" \n",
" \n",
" \n",
" count \n",
" 400.000000 \n",
" 400.00000 \n",
" \n",
" \n",
" mean \n",
" 9.370525 \n",
" 1.66740 \n",
" \n",
" \n",
" std \n",
" 5.796400 \n",
" 1.10816 \n",
" \n",
" \n",
" min \n",
" 0.010000 \n",
" 0.01000 \n",
" \n",
" \n",
" 25% \n",
" 4.325000 \n",
" 0.70750 \n",
" \n",
" \n",
" 50% \n",
" 9.020000 \n",
" 1.61500 \n",
" \n",
" \n",
" 75% \n",
" 13.747500 \n",
" 2.40000 \n",
" \n",
" \n",
" max \n",
" 22.270000 \n",
" 4.88000 \n",
" \n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Time Weight\n",
"count 400.000000 400.00000\n",
"mean 9.370525 1.66740\n",
"std 5.796400 1.10816\n",
"min 0.010000 0.01000\n",
"25% 4.325000 0.70750\n",
"50% 9.020000 1.61500\n",
"75% 13.747500 2.40000\n",
"max 22.270000 4.88000"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#If you run the \"describe\" function, it will show you LOTS of useful stats for both colunmns\n",
"___._______()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Additionally calculate the skewness and kurtosis for each column\n",
"\n",
"#You can use your dataframe's built-in methods for that:\n",
"\n",
"____.skew()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"____.kurtosis()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Finally, find the smallest and biggest data values:\n",
"\n",
"____.____()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"____.____()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Seaborn Visualisations\n",
"We will be using Seaborn for more complex visualisations\n",
"Fun fact: did you know that Seaborn is imported as SNS because it's a character in the West Wing series (Samuel Norman Seaborn). Don't ask me..."
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import seaborn as sns # For visualisations\n",
"\n",
"#Run the pairplot function from seaborn on your data frame\n",
"\n",
"___.pairplot(___)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Run the scatterplot of Weight vs. Time on your dataframe\n",
"sns.___(x=\"Time\", y=\"___\", data=___)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Now generate smooth curves for the distributions of both variables\n",
"\n",
"sns.distplot(time_weight_bait_data[\"_\"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sns.distplot(time_weight_bait_data[\"_\"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Create a new markdown cell below and write a summary of your findings from the plots above\n",
"#Use headings of different sizes"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Digging deeper into the correlation"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Create a regplot to figure out the correlation\n",
"\n",
"sns.regplot(x=\"\", y=\"\", data=_)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#Import stats from scipy\n",
"\n",
"from ___ import ___\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Use the pearsonr method to find the correlation details \n",
"# Is it positive or negative?\n",
"# Is it statistically significant?\n",
"\n",
"___.___(___,___)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Define a named function that calculates the R-squared using what we did in the previous step\n",
"\n",
"d__ r2(x,y):\n",
" return ___.___(_,_)[0]**2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# You can experiment with some other functions like jointplot\n",
"\n",
"sns.jointplot(x=\"Time\", y=\"Weight\", data=time_weight_bait_data, kind=\"reg\", stat_func=r2)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Create a new markdown cell below and write a summary of your findings from the plots above\n",
"#Use headings of different sizes"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## [This is the end of your tutorial.]\n",
"For CW1, we will cover a few more concepts next week.\n",
"\n",
"If you finished this early, have a look at the sklearn and numpy docs and examples online."
]
}
],
"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": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}