Importing Data

importing_data.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Without Arguments"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "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>The following stock data was collect on 2016-AUG-25 from an unknown source</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>These kind of ocmments are not very useful</th>\n",
       "      <td>are they?</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>probably should just throw this line away too</th>\n",
       "      <td>but not the next since those are column labels</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>name Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th># So that line you just read has all the column headers labels</th>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                   The following stock data was collect on 2016-AUG-25 from an unknown source\n",
       "These kind of ocmments are not very useful                                                  are they?                        \n",
       "probably should just throw this line away too          but not the next since those are column labels                        \n",
       "name Jan Feb Mar Apr May Jun Jul Aug Sep Oct No...                                                NaN                        \n",
       "# So that line you just read has all the column...                                                NaN                        "
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('messy_stock_data.tsv')\n",
    "df.head(4)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# With Arguments"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "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>name</th>\n",
       "      <th>Jan</th>\n",
       "      <th>Feb</th>\n",
       "      <th>Mar</th>\n",
       "      <th>Apr</th>\n",
       "      <th>May</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>IBM</td>\n",
       "      <td>156.08</td>\n",
       "      <td>160.01</td>\n",
       "      <td>159.81</td>\n",
       "      <td>165.22</td>\n",
       "      <td>172.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>MSFT</td>\n",
       "      <td>45.51</td>\n",
       "      <td>43.08</td>\n",
       "      <td>42.13</td>\n",
       "      <td>43.47</td>\n",
       "      <td>47.53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>GOOGLE</td>\n",
       "      <td>512.42</td>\n",
       "      <td>537.99</td>\n",
       "      <td>559.72</td>\n",
       "      <td>540.50</td>\n",
       "      <td>535.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>APPLE</td>\n",
       "      <td>110.64</td>\n",
       "      <td>125.43</td>\n",
       "      <td>125.97</td>\n",
       "      <td>127.29</td>\n",
       "      <td>128.76</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     name     Jan     Feb     Mar     Apr     May\n",
       "0     IBM  156.08  160.01  159.81  165.22  172.25\n",
       "1    MSFT   45.51   43.08   42.13   43.47   47.53\n",
       "2  GOOGLE  512.42  537.99  559.72  540.50  535.24\n",
       "3   APPLE  110.64  125.43  125.97  127.29  128.76"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('messy_stock_data.tsv', header=3, delimiter=' ', comment='#', index_col=False, usecols=[0,1,2,3,4,5])\n",
    "df.head(4)"
   ]
  }
 ],
 "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}