└── PyCharm March 2018 Webcast.ipynb


/PyCharm March 2018 Webcast.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "markdown",
   5 |    "metadata": {},
   6 |    "source": [
   7 |     "# A Day in the Life (of a Python Data Scientist)\n",
   8 |     "``@__mharrison__``"
   9 |    ]
  10 |   },
  11 |   {
  12 |    "cell_type": "code",
  13 |    "execution_count": 3,
  14 |    "metadata": {},
  15 |    "outputs": [],
  16 |    "source": [
  17 |     "class Tweet(object):\n",
  18 |     "    def __init__(self, embed_str=None):\n",
  19 |     "        self.embed_str = embed_str\n",
  20 |     "\n",
  21 |     "    def _repr_html_(self):\n",
  22 |     "        return self.embed_str\n",
  23 |     "\n",
  24 |     "s = (\"\"\"\n",
  25 |     "<blockquote class=\"twitter-tweet\" data-lang=\"en\"><p lang=\"en\" dir=\"ltr\">In Data Science, 80% of time spent prepare data, 20% of time spent complain about need for prepare data.</p>&mdash; Big Data Borat (@BigDataBorat) <a href=\"https://twitter.com/BigDataBorat/status/306596352991830016?ref_src=twsrc%5Etfw\">February 27, 2013</a></blockquote>\n",
  26 |     "<script async src=\"https://platform.twitter.com/widgets.js\" charset=\"utf-8\"></script>\n",
  27 |     "\"\"\")"
  28 |    ]
  29 |   },
  30 |   {
  31 |    "cell_type": "code",
  32 |    "execution_count": 4,
  33 |    "metadata": {},
  34 |    "outputs": [
  35 |     {
  36 |      "data": {
  37 |       "text/html": [
  38 |        "\n",
  39 |        "<a href=\"https://www.amazon.com/Illustrated-Guide-Python-Walkthrough-Illustrations/dp/1977921752/ref=as_li_ss_il?ie=UTF8&linkCode=li2&tag=pythonnotebook-20&linkId=82cb0f0aab6f7ad418b04ec98856bbec\" target=\"_blank\"><img border=\"0\" src=\"//ws-na.amazon-adsystem.com/widgets/q?_encoding=UTF8&ASIN=1977921752&Format=_SL160_&ID=AsinImage&MarketPlace=US&ServiceVersion=20070822&WS=1&tag=pythonnotebook-20\" ></a><img src=\"https://ir-na.amazon-adsystem.com/e/ir?t=pythonnotebook-20&l=li2&o=1&a=1977921752\" width=\"1\" height=\"1\" border=\"0\" alt=\"\" style=\"border:none !important; margin:0px !important;\" />\n",
  40 |        "<!--<iframe style=\"width:120px;height:240px;\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" frameborder=\"0\" src=\"//ws-na.amazon-adsystem.com/widgets/q?ServiceVersion=20070822&OneJS=1&Operation=GetAdHtml&MarketPlace=US&source=ss&ref=as_ss_li_til&ad_type=product_link&tracking_id=pythonnotebook-20&marketplace=amazon&region=US&placement=1977921752&asins=1977921752&linkId=df0298114b7f5e9996feb2b4618be713&show_border=true&link_opens_in_new_window=true\"></iframe>\n",
  41 |        "-->\n"
  42 |       ],
  43 |       "text/plain": [
  44 |        "<__main__.Tweet at 0x111ef1a58>"
  45 |       ]
  46 |      },
  47 |      "execution_count": 4,
  48 |      "metadata": {},
  49 |      "output_type": "execute_result"
  50 |     }
  51 |    ],
  52 |    "source": [
  53 |     "Tweet(\"\"\"\n",
  54 |     "<a href=\"https://www.amazon.com/Illustrated-Guide-Python-Walkthrough-Illustrations/dp/1977921752/ref=as_li_ss_il?ie=UTF8&linkCode=li2&tag=pythonnotebook-20&linkId=82cb0f0aab6f7ad418b04ec98856bbec\" target=\"_blank\"><img border=\"0\" src=\"//ws-na.amazon-adsystem.com/widgets/q?_encoding=UTF8&ASIN=1977921752&Format=_SL160_&ID=AsinImage&MarketPlace=US&ServiceVersion=20070822&WS=1&tag=pythonnotebook-20\" ></a><img src=\"https://ir-na.amazon-adsystem.com/e/ir?t=pythonnotebook-20&l=li2&o=1&a=1977921752\" width=\"1\" height=\"1\" border=\"0\" alt=\"\" style=\"border:none !important; margin:0px !important;\" />\n",
  55 |     "<!--<iframe style=\"width:120px;height:240px;\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" frameborder=\"0\" src=\"//ws-na.amazon-adsystem.com/widgets/q?ServiceVersion=20070822&OneJS=1&Operation=GetAdHtml&MarketPlace=US&source=ss&ref=as_ss_li_til&ad_type=product_link&tracking_id=pythonnotebook-20&marketplace=amazon&region=US&placement=1977921752&asins=1977921752&linkId=df0298114b7f5e9996feb2b4618be713&show_border=true&link_opens_in_new_window=true\"></iframe>\n",
  56 |     "-->\n",
  57 |     "\"\"\")"
  58 |    ]
  59 |   },
  60 |   {
  61 |    "cell_type": "code",
  62 |    "execution_count": 5,
  63 |    "metadata": {},
  64 |    "outputs": [
  65 |     {
  66 |      "data": {
  67 |       "text/html": [
  68 |        "\n",
  69 |        "<blockquote class=\"twitter-tweet\" data-lang=\"en\"><p lang=\"en\" dir=\"ltr\">In Data Science, 80% of time spent prepare data, 20% of time spent complain about need for prepare data.</p>&mdash; Big Data Borat (@BigDataBorat) <a href=\"https://twitter.com/BigDataBorat/status/306596352991830016?ref_src=twsrc%5Etfw\">February 27, 2013</a></blockquote>\n",
  70 |        "<script async src=\"https://platform.twitter.com/widgets.js\" charset=\"utf-8\"></script>\n"
  71 |       ],
  72 |       "text/plain": [
  73 |        "<__main__.Tweet at 0x111ef1748>"
  74 |       ]
  75 |      },
  76 |      "execution_count": 5,
  77 |      "metadata": {},
  78 |      "output_type": "execute_result"
  79 |     }
  80 |    ],
  81 |    "source": [
  82 |     "Tweet(s)"
  83 |    ]
  84 |   },
  85 |   {
  86 |    "cell_type": "code",
  87 |    "execution_count": 6,
  88 |    "metadata": {},
  89 |    "outputs": [
  90 |     {
  91 |      "name": "stderr",
  92 |      "output_type": "stream",
  93 |      "text": [
  94 |       "/Users/matt/.env/36/lib/python3.6/site-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.\n",
  95 |       "  \"This module will be removed in 0.20.\", DeprecationWarning)\n"
  96 |      ]
  97 |     }
  98 |    ],
  99 |    "source": [
 100 |     "%matplotlib inline\n",
 101 |     "import matplotlib.pyplot as plt\n",
 102 |     "import pandas as pd\n",
 103 |     "from sklearn import ensemble, model_selection, preprocessing, tree\n",
 104 |     "from yellowbrick.classifier import ROCAUC\n",
 105 |     "from yellowbrick.classifier import ClassificationReport, ConfusionMatrix"
 106 |    ]
 107 |   },
 108 |   {
 109 |    "cell_type": "markdown",
 110 |    "metadata": {},
 111 |    "source": [
 112 |     "https://www.kaggle.com/mczielinski/bitcoin-historical-data"
 113 |    ]
 114 |   },
 115 |   {
 116 |    "cell_type": "code",
 117 |    "execution_count": 15,
 118 |    "metadata": {},
 119 |    "outputs": [
 120 |     {
 121 |      "name": "stdout",
 122 |      "output_type": "stream",
 123 |      "text": [
 124 |       "CPU times: user 2.47 s, sys: 333 ms, total: 2.81 s\n",
 125 |       "Wall time: 3.19 s\n"
 126 |      ]
 127 |     }
 128 |    ],
 129 |    "source": [
 130 |     "%%time\n",
 131 |     "bit_df = pd.read_csv('../ORA-ML-Class-Reg/data/coinbaseUSD_1-min_data_2014-12-01_to_2018-01-08.csv')\n",
 132 |     "bit_df['date'] = pd.to_datetime(bit_df.Timestamp, unit='s')"
 133 |    ]
 134 |   },
 135 |   {
 136 |    "cell_type": "code",
 137 |    "execution_count": 25,
 138 |    "metadata": {},
 139 |    "outputs": [
 140 |     {
 141 |      "name": "stdout",
 142 |      "output_type": "stream",
 143 |      "text": [
 144 |       "CPU times: user 2.64 s, sys: 513 ms, total: 3.16 s\n",
 145 |       "Wall time: 3.87 s\n"
 146 |      ]
 147 |     }
 148 |    ],
 149 |    "source": [
 150 |     "%%time\n",
 151 |     "bit_df = pd.read_csv('../ORA-ML-Class-Reg/data/coinbaseUSD_1-min_data_2014-12-01_to_2018-01-08.csv')\n",
 152 |     "bit_df['date'] = pd.to_datetime(bit_df.Timestamp, unit='s')\n",
 153 |     "bit_df = (\n",
 154 |     "    bit_df.set_index('date')\n",
 155 |     "        .rename(columns={'Open':'open', 'High': 'hi', 'Low': 'lo', \n",
 156 |     "                       'Close': 'close', 'Volume_(BTC)': 'vol_btc',\n",
 157 |     "                       'Volume_(Currency)': 'vol_cur', \n",
 158 |     "                       'Weighted_Price': 'wp', 'Timestamp': 'ts'})\n",
 159 |     "        .resample('d')\n",
 160 |     "        .agg({'open': 'first', 'hi': 'mean', \n",
 161 |     "    'lo': 'mean', 'close': 'last', 'vol_btc': 'sum',\n",
 162 |     "    'vol_cur': 'sum', 'wp': 'mean', 'ts': 'min'})\n",
 163 |     "    .iloc[-1000:]\n",
 164 |     "    .assign(buy = lambda x: (x.close.shift(-1) > x.close).astype(int))\n",
 165 |     "    .iloc[:-1]\n",
 166 |     "    \n",
 167 |     ")\n"
 168 |    ]
 169 |   },
 170 |   {
 171 |    "cell_type": "code",
 172 |    "execution_count": 23,
 173 |    "metadata": {},
 174 |    "outputs": [
 175 |     {
 176 |      "name": "stdout",
 177 |      "output_type": "stream",
 178 |      "text": [
 179 |       "['Close', 'High', 'Low', 'Open', 'T', 'Timestamp', 'Weighted_Price', '_AXIS_ALIASES', '_AXIS_IALIASES', '_AXIS_LEN', '_AXIS_NAMES', '_AXIS_NUMBERS', '_AXIS_ORDERS', '_AXIS_REVERSED', '_AXIS_SLICEMAP', '__abs__', '__add__', '__and__', '__array__', '__array_wrap__', '__bool__', '__bytes__', '__class__', '__contains__', '__copy__', '__deepcopy__', '__delattr__', '__delitem__', '__dict__', '__dir__', '__div__', '__doc__', '__eq__', '__finalize__', '__floordiv__', '__format__', '__ge__', '__getattr__', '__getattribute__', '__getitem__', '__getstate__', '__gt__', '__hash__', '__iadd__', '__iand__', '__ifloordiv__', '__imod__', '__imul__', '__init__', '__init_subclass__', '__invert__', '__ior__', '__ipow__', '__isub__', '__iter__', '__itruediv__', '__ixor__', '__le__', '__len__', '__lt__', '__mod__', '__module__', '__mul__', '__ne__', '__neg__', '__new__', '__nonzero__', '__or__', '__pow__', '__radd__', '__rand__', '__rdiv__', '__reduce__', '__reduce_ex__', '__repr__', '__rfloordiv__', '__rmod__', '__rmul__', '__ror__', '__round__', '__rpow__', '__rsub__', '__rtruediv__', '__rxor__', '__setattr__', '__setitem__', '__setstate__', '__sizeof__', '__str__', '__sub__', '__subclasshook__', '__truediv__', '__unicode__', '__weakref__', '__xor__', '_accessors', '_add_numeric_operations', '_add_series_only_operations', '_add_series_or_dataframe_operations', '_agg_by_level', '_agg_doc', '_aggregate', '_aggregate_multiple_funcs', '_align_frame', '_align_series', '_apply_broadcast', '_apply_empty_result', '_apply_raw', '_apply_standard', '_at', '_box_col_values', '_box_item_values', '_builtin_table', '_check_inplace_setting', '_check_is_chained_assignment_possible', '_check_percentile', '_check_setitem_copy', '_clear_item_cache', '_clip_with_one_bound', '_clip_with_scalar', '_combine_const', '_combine_frame', '_combine_match_columns', '_combine_match_index', '_combine_series', '_combine_series_infer', '_compare_frame', '_compare_frame_evaluate', '_consolidate', '_consolidate_inplace', '_construct_axes_dict', '_construct_axes_dict_for_slice', '_construct_axes_dict_from', '_construct_axes_from_arguments', '_constructor', '_constructor_expanddim', '_constructor_sliced', '_convert', '_count_level', '_create_indexer', '_cython_table', '_deprecations', '_dir_additions', '_dir_deletions', '_drop_axis', '_ensure_valid_index', '_expand_axes', '_flex_compare_frame', '_from_arrays', '_from_axes', '_get_agg_axis', '_get_axis', '_get_axis_name', '_get_axis_number', '_get_axis_resolvers', '_get_block_manager_axis', '_get_bool_data', '_get_cacher', '_get_index_resolvers', '_get_item_cache', '_get_numeric_data', '_get_valid_indices', '_get_value', '_get_values', '_getitem_array', '_getitem_column', '_getitem_frame', '_getitem_multilevel', '_getitem_slice', '_gotitem', '_iat', '_iget_item_cache', '_iloc', '_indexed_same', '_info_axis', '_info_axis_name', '_info_axis_number', '_info_repr', '_init_dict', '_init_mgr', '_init_ndarray', '_internal_names', '_internal_names_set', '_is_builtin_func', '_is_cached', '_is_cython_func', '_is_datelike_mixed_type', '_is_mixed_type', '_is_numeric_mixed_type', '_is_view', '_ix', '_ixs', '_join_compat', '_loc', '_maybe_cache_changed', '_maybe_update_cacher', '_metadata', '_needs_reindex_multi', '_obj_with_exclusions', '_protect_consolidate', '_reduce', '_reindex_axes', '_reindex_axis', '_reindex_columns', '_reindex_index', '_reindex_multi', '_reindex_with_indexers', '_repr_data_resource_', '_repr_fits_horizontal_', '_repr_fits_vertical_', '_repr_html_', '_repr_latex_', '_reset_cache', '_reset_cacher', '_sanitize_column', '_selected_obj', '_selection', '_selection_list', '_selection_name', '_series', '_set_as_cached', '_set_axis', '_set_axis_name', '_set_is_copy', '_set_item', '_set_value', '_setitem_array', '_setitem_frame', '_setitem_slice', '_setup_axes', '_shallow_copy', '_slice', '_stat_axis', '_stat_axis_name', '_stat_axis_number', '_take', '_to_dict_of_blocks', '_try_aggregate_string_function', '_typ', '_unpickle_frame_compat', '_unpickle_matrix_compat', '_update_inplace', '_validate_dtype', '_values', '_where', '_xs', 'abs', 'add', 'add_prefix', 'add_suffix', 'agg', 'aggregate', 'align', 'all', 'any', 'append', 'apply', 'applymap', 'as_matrix', 'asfreq', 'asof', 'assign', 'astype', 'at', 'at_time', 'axes', 'between_time', 'bfill', 'bool', 'boxplot', 'clip', 'clip_lower', 'clip_upper', 'columns', 'combine', 'combine_first', 'compound', 'copy', 'corr', 'corrwith', 'count', 'cov', 'cummax', 'cummin', 'cumprod', 'cumsum', 'date', 'describe', 'diff', 'div', 'divide', 'dot', 'drop', 'drop_duplicates', 'dropna', 'dtypes', 'duplicated', 'empty', 'eq', 'equals', 'eval', 'ewm', 'expanding', 'ffill', 'fillna', 'filter', 'first', 'first_valid_index', 'floordiv', 'from_dict', 'from_items', 'from_records', 'ftypes', 'ge', 'get', 'get_dtype_counts', 'get_ftype_counts', 'get_values', 'groupby', 'gt', 'head', 'hist', 'iat', 'idxmax', 'idxmin', 'iloc', 'index', 'infer_objects', 'info', 'insert', 'interpolate', 'is_copy', 'isin', 'isna', 'isnull', 'items', 'iteritems', 'iterrows', 'itertuples', 'ix', 'join', 'keys', 'kurt', 'kurtosis', 'last', 'last_valid_index', 'le', 'loc', 'lookup', 'lt', 'mad', 'mask', 'max', 'mean', 'median', 'melt', 'memory_usage', 'merge', 'min', 'mod', 'mode', 'mul', 'multiply', 'ndim', 'ne', 'nlargest', 'notna', 'notnull', 'nsmallest', 'nunique', 'pct_change', 'pipe', 'pivot', 'pivot_table', 'plot', 'pop', 'pow', 'prod', 'product', 'quantile', 'query', 'radd', 'rank', 'rdiv', 'reindex', 'reindex_axis', 'reindex_like', 'rename', 'rename_axis', 'reorder_levels', 'replace', 'resample', 'reset_index', 'rfloordiv', 'rmod', 'rmul', 'rolling', 'round', 'rpow', 'rsub', 'rtruediv', 'sample', 'select', 'select_dtypes', 'sem', 'set_axis', 'set_index', 'shape', 'shift', 'size', 'skew', 'slice_shift', 'sort_index', 'sort_values', 'squeeze', 'stack', 'std', 'style', 'sub', 'subtract', 'sum', 'swapaxes', 'swaplevel', 'tail', 'take', 'to_clipboard', 'to_csv', 'to_dense', 'to_dict', 'to_excel', 'to_feather', 'to_gbq', 'to_hdf', 'to_html', 'to_json', 'to_latex', 'to_msgpack', 'to_panel', 'to_parquet', 'to_period', 'to_pickle', 'to_records', 'to_sparse', 'to_sql', 'to_stata', 'to_string', 'to_timestamp', 'to_xarray', 'transform', 'transpose', 'truediv', 'truncate', 'tshift', 'tz_convert', 'tz_localize', 'unstack', 'update', 'values', 'var', 'where', 'xs']\n"
 180 |      ]
 181 |     }
 182 |    ],
 183 |    "source": [
 184 |     "print(dir(bit_df))"
 185 |    ]
 186 |   },
 187 |   {
 188 |    "cell_type": "code",
 189 |    "execution_count": null,
 190 |    "metadata": {},
 191 |    "outputs": [],
 192 |    "source": []
 193 |   },
 194 |   {
 195 |    "cell_type": "code",
 196 |    "execution_count": 8,
 197 |    "metadata": {
 198 |     "scrolled": true
 199 |    },
 200 |    "outputs": [
 201 |     {
 202 |      "data": {
 203 |       "text/html": [
 204 |        "<div>\n",
 205 |        "<style scoped>\n",
 206 |        "    .dataframe tbody tr th:only-of-type {\n",
 207 |        "        vertical-align: middle;\n",
 208 |        "    }\n",
 209 |        "\n",
 210 |        "    .dataframe tbody tr th {\n",
 211 |        "        vertical-align: top;\n",
 212 |        "    }\n",
 213 |        "\n",
 214 |        "    .dataframe thead th {\n",
 215 |        "        text-align: right;\n",
 216 |        "    }\n",
 217 |        "</style>\n",
 218 |        "<table border=\"1\" class=\"dataframe\">\n",
 219 |        "  <thead>\n",
 220 |        "    <tr style=\"text-align: right;\">\n",
 221 |        "      <th></th>\n",
 222 |        "      <th>Timestamp</th>\n",
 223 |        "      <th>Open</th>\n",
 224 |        "      <th>High</th>\n",
 225 |        "      <th>Low</th>\n",
 226 |        "      <th>Close</th>\n",
 227 |        "      <th>Volume_(BTC)</th>\n",
 228 |        "      <th>Volume_(Currency)</th>\n",
 229 |        "      <th>Weighted_Price</th>\n",
 230 |        "    </tr>\n",
 231 |        "  </thead>\n",
 232 |        "  <tbody>\n",
 233 |        "    <tr>\n",
 234 |        "      <th>0</th>\n",
 235 |        "      <td>1417411980</td>\n",
 236 |        "      <td>300.00</td>\n",
 237 |        "      <td>300.00</td>\n",
 238 |        "      <td>300.00</td>\n",
 239 |        "      <td>300.00</td>\n",
 240 |        "      <td>0.010000</td>\n",
 241 |        "      <td>3.000000</td>\n",
 242 |        "      <td>300.000000</td>\n",
 243 |        "    </tr>\n",
 244 |        "    <tr>\n",
 245 |        "      <th>1</th>\n",
 246 |        "      <td>1417412040</td>\n",
 247 |        "      <td>300.00</td>\n",
 248 |        "      <td>300.00</td>\n",
 249 |        "      <td>300.00</td>\n",
 250 |        "      <td>300.00</td>\n",
 251 |        "      <td>0.010000</td>\n",
 252 |        "      <td>3.000000</td>\n",
 253 |        "      <td>300.000000</td>\n",
 254 |        "    </tr>\n",
 255 |        "    <tr>\n",
 256 |        "      <th>2</th>\n",
 257 |        "      <td>1417412100</td>\n",
 258 |        "      <td>300.00</td>\n",
 259 |        "      <td>300.00</td>\n",
 260 |        "      <td>300.00</td>\n",
 261 |        "      <td>300.00</td>\n",
 262 |        "      <td>0.010000</td>\n",
 263 |        "      <td>3.000000</td>\n",
 264 |        "      <td>300.000000</td>\n",
 265 |        "    </tr>\n",
 266 |        "    <tr>\n",
 267 |        "      <th>3</th>\n",
 268 |        "      <td>1417412160</td>\n",
 269 |        "      <td>300.00</td>\n",
 270 |        "      <td>300.00</td>\n",
 271 |        "      <td>300.00</td>\n",
 272 |        "      <td>300.00</td>\n",
 273 |        "      <td>0.010000</td>\n",
 274 |        "      <td>3.000000</td>\n",
 275 |        "      <td>300.000000</td>\n",
 276 |        "    </tr>\n",
 277 |        "    <tr>\n",
 278 |        "      <th>4</th>\n",
 279 |        "      <td>1417412220</td>\n",
 280 |        "      <td>300.00</td>\n",
 281 |        "      <td>300.00</td>\n",
 282 |        "      <td>300.00</td>\n",
 283 |        "      <td>300.00</td>\n",
 284 |        "      <td>0.010000</td>\n",
 285 |        "      <td>3.000000</td>\n",
 286 |        "      <td>300.000000</td>\n",
 287 |        "    </tr>\n",
 288 |        "    <tr>\n",
 289 |        "      <th>5</th>\n",
 290 |        "      <td>1417412280</td>\n",
 291 |        "      <td>300.00</td>\n",
 292 |        "      <td>300.00</td>\n",
 293 |        "      <td>300.00</td>\n",
 294 |        "      <td>300.00</td>\n",
 295 |        "      <td>0.010000</td>\n",
 296 |        "      <td>3.000000</td>\n",
 297 |        "      <td>300.000000</td>\n",
 298 |        "    </tr>\n",
 299 |        "    <tr>\n",
 300 |        "      <th>6</th>\n",
 301 |        "      <td>1417412340</td>\n",
 302 |        "      <td>300.00</td>\n",
 303 |        "      <td>300.00</td>\n",
 304 |        "      <td>300.00</td>\n",
 305 |        "      <td>300.00</td>\n",
 306 |        "      <td>0.010000</td>\n",
 307 |        "      <td>3.000000</td>\n",
 308 |        "      <td>300.000000</td>\n",
 309 |        "    </tr>\n",
 310 |        "    <tr>\n",
 311 |        "      <th>7</th>\n",
 312 |        "      <td>1417412400</td>\n",
 313 |        "      <td>300.00</td>\n",
 314 |        "      <td>300.00</td>\n",
 315 |        "      <td>300.00</td>\n",
 316 |        "      <td>300.00</td>\n",
 317 |        "      <td>0.010000</td>\n",
 318 |        "      <td>3.000000</td>\n",
 319 |        "      <td>300.000000</td>\n",
 320 |        "    </tr>\n",
 321 |        "    <tr>\n",
 322 |        "      <th>8</th>\n",
 323 |        "      <td>1417412460</td>\n",
 324 |        "      <td>300.00</td>\n",
 325 |        "      <td>300.00</td>\n",
 326 |        "      <td>300.00</td>\n",
 327 |        "      <td>300.00</td>\n",
 328 |        "      <td>0.010000</td>\n",
 329 |        "      <td>3.000000</td>\n",
 330 |        "      <td>300.000000</td>\n",
 331 |        "    </tr>\n",
 332 |        "    <tr>\n",
 333 |        "      <th>9</th>\n",
 334 |        "      <td>1417412520</td>\n",
 335 |        "      <td>300.00</td>\n",
 336 |        "      <td>300.00</td>\n",
 337 |        "      <td>300.00</td>\n",
 338 |        "      <td>300.00</td>\n",
 339 |        "      <td>0.010000</td>\n",
 340 |        "      <td>3.000000</td>\n",
 341 |        "      <td>300.000000</td>\n",
 342 |        "    </tr>\n",
 343 |        "    <tr>\n",
 344 |        "      <th>10</th>\n",
 345 |        "      <td>1417412580</td>\n",
 346 |        "      <td>300.00</td>\n",
 347 |        "      <td>300.00</td>\n",
 348 |        "      <td>300.00</td>\n",
 349 |        "      <td>300.00</td>\n",
 350 |        "      <td>0.010000</td>\n",
 351 |        "      <td>3.000000</td>\n",
 352 |        "      <td>300.000000</td>\n",
 353 |        "    </tr>\n",
 354 |        "    <tr>\n",
 355 |        "      <th>11</th>\n",
 356 |        "      <td>1417412640</td>\n",
 357 |        "      <td>300.00</td>\n",
 358 |        "      <td>300.00</td>\n",
 359 |        "      <td>300.00</td>\n",
 360 |        "      <td>300.00</td>\n",
 361 |        "      <td>0.010000</td>\n",
 362 |        "      <td>3.000000</td>\n",
 363 |        "      <td>300.000000</td>\n",
 364 |        "    </tr>\n",
 365 |        "    <tr>\n",
 366 |        "      <th>12</th>\n",
 367 |        "      <td>1417412700</td>\n",
 368 |        "      <td>300.00</td>\n",
 369 |        "      <td>300.00</td>\n",
 370 |        "      <td>300.00</td>\n",
 371 |        "      <td>300.00</td>\n",
 372 |        "      <td>0.010000</td>\n",
 373 |        "      <td>3.000000</td>\n",
 374 |        "      <td>300.000000</td>\n",
 375 |        "    </tr>\n",
 376 |        "    <tr>\n",
 377 |        "      <th>13</th>\n",
 378 |        "      <td>1417412760</td>\n",
 379 |        "      <td>300.00</td>\n",
 380 |        "      <td>300.00</td>\n",
 381 |        "      <td>300.00</td>\n",
 382 |        "      <td>300.00</td>\n",
 383 |        "      <td>0.010000</td>\n",
 384 |        "      <td>3.000000</td>\n",
 385 |        "      <td>300.000000</td>\n",
 386 |        "    </tr>\n",
 387 |        "    <tr>\n",
 388 |        "      <th>14</th>\n",
 389 |        "      <td>1417412820</td>\n",
 390 |        "      <td>300.00</td>\n",
 391 |        "      <td>300.00</td>\n",
 392 |        "      <td>300.00</td>\n",
 393 |        "      <td>300.00</td>\n",
 394 |        "      <td>0.010000</td>\n",
 395 |        "      <td>3.000000</td>\n",
 396 |        "      <td>300.000000</td>\n",
 397 |        "    </tr>\n",
 398 |        "    <tr>\n",
 399 |        "      <th>15</th>\n",
 400 |        "      <td>1417412880</td>\n",
 401 |        "      <td>300.00</td>\n",
 402 |        "      <td>300.00</td>\n",
 403 |        "      <td>300.00</td>\n",
 404 |        "      <td>300.00</td>\n",
 405 |        "      <td>0.010000</td>\n",
 406 |        "      <td>3.000000</td>\n",
 407 |        "      <td>300.000000</td>\n",
 408 |        "    </tr>\n",
 409 |        "    <tr>\n",
 410 |        "      <th>16</th>\n",
 411 |        "      <td>1417412940</td>\n",
 412 |        "      <td>300.00</td>\n",
 413 |        "      <td>300.00</td>\n",
 414 |        "      <td>300.00</td>\n",
 415 |        "      <td>300.00</td>\n",
 416 |        "      <td>0.010000</td>\n",
 417 |        "      <td>3.000000</td>\n",
 418 |        "      <td>300.000000</td>\n",
 419 |        "    </tr>\n",
 420 |        "    <tr>\n",
 421 |        "      <th>17</th>\n",
 422 |        "      <td>1417413000</td>\n",
 423 |        "      <td>300.00</td>\n",
 424 |        "      <td>300.00</td>\n",
 425 |        "      <td>300.00</td>\n",
 426 |        "      <td>300.00</td>\n",
 427 |        "      <td>0.010000</td>\n",
 428 |        "      <td>3.000000</td>\n",
 429 |        "      <td>300.000000</td>\n",
 430 |        "    </tr>\n",
 431 |        "    <tr>\n",
 432 |        "      <th>18</th>\n",
 433 |        "      <td>1417413060</td>\n",
 434 |        "      <td>300.00</td>\n",
 435 |        "      <td>300.00</td>\n",
 436 |        "      <td>300.00</td>\n",
 437 |        "      <td>300.00</td>\n",
 438 |        "      <td>0.010000</td>\n",
 439 |        "      <td>3.000000</td>\n",
 440 |        "      <td>300.000000</td>\n",
 441 |        "    </tr>\n",
 442 |        "    <tr>\n",
 443 |        "      <th>19</th>\n",
 444 |        "      <td>1417413120</td>\n",
 445 |        "      <td>300.00</td>\n",
 446 |        "      <td>300.00</td>\n",
 447 |        "      <td>300.00</td>\n",
 448 |        "      <td>300.00</td>\n",
 449 |        "      <td>0.010000</td>\n",
 450 |        "      <td>3.000000</td>\n",
 451 |        "      <td>300.000000</td>\n",
 452 |        "    </tr>\n",
 453 |        "    <tr>\n",
 454 |        "      <th>20</th>\n",
 455 |        "      <td>1417413180</td>\n",
 456 |        "      <td>300.00</td>\n",
 457 |        "      <td>300.00</td>\n",
 458 |        "      <td>300.00</td>\n",
 459 |        "      <td>300.00</td>\n",
 460 |        "      <td>0.010000</td>\n",
 461 |        "      <td>3.000000</td>\n",
 462 |        "      <td>300.000000</td>\n",
 463 |        "    </tr>\n",
 464 |        "    <tr>\n",
 465 |        "      <th>21</th>\n",
 466 |        "      <td>1417413240</td>\n",
 467 |        "      <td>300.00</td>\n",
 468 |        "      <td>300.00</td>\n",
 469 |        "      <td>300.00</td>\n",
 470 |        "      <td>300.00</td>\n",
 471 |        "      <td>0.010000</td>\n",
 472 |        "      <td>3.000000</td>\n",
 473 |        "      <td>300.000000</td>\n",
 474 |        "    </tr>\n",
 475 |        "    <tr>\n",
 476 |        "      <th>22</th>\n",
 477 |        "      <td>1417413300</td>\n",
 478 |        "      <td>300.00</td>\n",
 479 |        "      <td>300.00</td>\n",
 480 |        "      <td>300.00</td>\n",
 481 |        "      <td>300.00</td>\n",
 482 |        "      <td>0.010000</td>\n",
 483 |        "      <td>3.000000</td>\n",
 484 |        "      <td>300.000000</td>\n",
 485 |        "    </tr>\n",
 486 |        "    <tr>\n",
 487 |        "      <th>23</th>\n",
 488 |        "      <td>1417413360</td>\n",
 489 |        "      <td>300.00</td>\n",
 490 |        "      <td>300.00</td>\n",
 491 |        "      <td>300.00</td>\n",
 492 |        "      <td>300.00</td>\n",
 493 |        "      <td>0.010000</td>\n",
 494 |        "      <td>3.000000</td>\n",
 495 |        "      <td>300.000000</td>\n",
 496 |        "    </tr>\n",
 497 |        "    <tr>\n",
 498 |        "      <th>24</th>\n",
 499 |        "      <td>1417413420</td>\n",
 500 |        "      <td>300.00</td>\n",
 501 |        "      <td>300.00</td>\n",
 502 |        "      <td>300.00</td>\n",
 503 |        "      <td>300.00</td>\n",
 504 |        "      <td>0.010000</td>\n",
 505 |        "      <td>3.000000</td>\n",
 506 |        "      <td>300.000000</td>\n",
 507 |        "    </tr>\n",
 508 |        "    <tr>\n",
 509 |        "      <th>25</th>\n",
 510 |        "      <td>1417413480</td>\n",
 511 |        "      <td>300.00</td>\n",
 512 |        "      <td>300.00</td>\n",
 513 |        "      <td>300.00</td>\n",
 514 |        "      <td>300.00</td>\n",
 515 |        "      <td>0.010000</td>\n",
 516 |        "      <td>3.000000</td>\n",
 517 |        "      <td>300.000000</td>\n",
 518 |        "    </tr>\n",
 519 |        "    <tr>\n",
 520 |        "      <th>26</th>\n",
 521 |        "      <td>1417413540</td>\n",
 522 |        "      <td>300.00</td>\n",
 523 |        "      <td>300.00</td>\n",
 524 |        "      <td>300.00</td>\n",
 525 |        "      <td>300.00</td>\n",
 526 |        "      <td>0.010000</td>\n",
 527 |        "      <td>3.000000</td>\n",
 528 |        "      <td>300.000000</td>\n",
 529 |        "    </tr>\n",
 530 |        "    <tr>\n",
 531 |        "      <th>27</th>\n",
 532 |        "      <td>1417413600</td>\n",
 533 |        "      <td>300.00</td>\n",
 534 |        "      <td>300.00</td>\n",
 535 |        "      <td>300.00</td>\n",
 536 |        "      <td>300.00</td>\n",
 537 |        "      <td>0.010000</td>\n",
 538 |        "      <td>3.000000</td>\n",
 539 |        "      <td>300.000000</td>\n",
 540 |        "    </tr>\n",
 541 |        "    <tr>\n",
 542 |        "      <th>28</th>\n",
 543 |        "      <td>1417413660</td>\n",
 544 |        "      <td>300.00</td>\n",
 545 |        "      <td>300.00</td>\n",
 546 |        "      <td>300.00</td>\n",
 547 |        "      <td>300.00</td>\n",
 548 |        "      <td>0.010000</td>\n",
 549 |        "      <td>3.000000</td>\n",
 550 |        "      <td>300.000000</td>\n",
 551 |        "    </tr>\n",
 552 |        "    <tr>\n",
 553 |        "      <th>29</th>\n",
 554 |        "      <td>1417413720</td>\n",
 555 |        "      <td>300.00</td>\n",
 556 |        "      <td>300.00</td>\n",
 557 |        "      <td>300.00</td>\n",
 558 |        "      <td>300.00</td>\n",
 559 |        "      <td>0.010000</td>\n",
 560 |        "      <td>3.000000</td>\n",
 561 |        "      <td>300.000000</td>\n",
 562 |        "    </tr>\n",
 563 |        "    <tr>\n",
 564 |        "      <th>...</th>\n",
 565 |        "      <td>...</td>\n",
 566 |        "      <td>...</td>\n",
 567 |        "      <td>...</td>\n",
 568 |        "      <td>...</td>\n",
 569 |        "      <td>...</td>\n",
 570 |        "      <td>...</td>\n",
 571 |        "      <td>...</td>\n",
 572 |        "      <td>...</td>\n",
 573 |        "    </tr>\n",
 574 |        "    <tr>\n",
 575 |        "      <th>1574244</th>\n",
 576 |        "      <td>1515367860</td>\n",
 577 |        "      <td>16329.79</td>\n",
 578 |        "      <td>16349.00</td>\n",
 579 |        "      <td>16329.79</td>\n",
 580 |        "      <td>16349.00</td>\n",
 581 |        "      <td>2.364011</td>\n",
 582 |        "      <td>38642.637918</td>\n",
 583 |        "      <td>16346.218304</td>\n",
 584 |        "    </tr>\n",
 585 |        "    <tr>\n",
 586 |        "      <th>1574245</th>\n",
 587 |        "      <td>1515367920</td>\n",
 588 |        "      <td>16349.00</td>\n",
 589 |        "      <td>16349.00</td>\n",
 590 |        "      <td>16329.00</td>\n",
 591 |        "      <td>16329.00</td>\n",
 592 |        "      <td>4.303270</td>\n",
 593 |        "      <td>70338.446619</td>\n",
 594 |        "      <td>16345.349090</td>\n",
 595 |        "    </tr>\n",
 596 |        "    <tr>\n",
 597 |        "      <th>1574246</th>\n",
 598 |        "      <td>1515367980</td>\n",
 599 |        "      <td>16329.01</td>\n",
 600 |        "      <td>16329.01</td>\n",
 601 |        "      <td>16300.00</td>\n",
 602 |        "      <td>16302.85</td>\n",
 603 |        "      <td>8.183248</td>\n",
 604 |        "      <td>133574.283340</td>\n",
 605 |        "      <td>16322.892267</td>\n",
 606 |        "    </tr>\n",
 607 |        "    <tr>\n",
 608 |        "      <th>1574247</th>\n",
 609 |        "      <td>1515368040</td>\n",
 610 |        "      <td>16302.84</td>\n",
 611 |        "      <td>16302.84</td>\n",
 612 |        "      <td>16279.74</td>\n",
 613 |        "      <td>16279.74</td>\n",
 614 |        "      <td>7.083056</td>\n",
 615 |        "      <td>115426.384420</td>\n",
 616 |        "      <td>16296.128527</td>\n",
 617 |        "    </tr>\n",
 618 |        "    <tr>\n",
 619 |        "      <th>1574248</th>\n",
 620 |        "      <td>1515368100</td>\n",
 621 |        "      <td>16279.75</td>\n",
 622 |        "      <td>16279.76</td>\n",
 623 |        "      <td>16266.06</td>\n",
 624 |        "      <td>16266.06</td>\n",
 625 |        "      <td>8.379655</td>\n",
 626 |        "      <td>136373.204380</td>\n",
 627 |        "      <td>16274.321438</td>\n",
 628 |        "    </tr>\n",
 629 |        "    <tr>\n",
 630 |        "      <th>1574249</th>\n",
 631 |        "      <td>1515368160</td>\n",
 632 |        "      <td>16266.07</td>\n",
 633 |        "      <td>16266.07</td>\n",
 634 |        "      <td>16266.06</td>\n",
 635 |        "      <td>16266.06</td>\n",
 636 |        "      <td>4.943145</td>\n",
 637 |        "      <td>80405.530720</td>\n",
 638 |        "      <td>16266.068487</td>\n",
 639 |        "    </tr>\n",
 640 |        "    <tr>\n",
 641 |        "      <th>1574250</th>\n",
 642 |        "      <td>1515368220</td>\n",
 643 |        "      <td>16266.06</td>\n",
 644 |        "      <td>16268.24</td>\n",
 645 |        "      <td>16266.06</td>\n",
 646 |        "      <td>16268.14</td>\n",
 647 |        "      <td>1.764196</td>\n",
 648 |        "      <td>28698.189067</td>\n",
 649 |        "      <td>16267.005559</td>\n",
 650 |        "    </tr>\n",
 651 |        "    <tr>\n",
 652 |        "      <th>1574251</th>\n",
 653 |        "      <td>1515368280</td>\n",
 654 |        "      <td>16268.13</td>\n",
 655 |        "      <td>16268.14</td>\n",
 656 |        "      <td>16268.13</td>\n",
 657 |        "      <td>16268.14</td>\n",
 658 |        "      <td>1.207304</td>\n",
 659 |        "      <td>19640.595763</td>\n",
 660 |        "      <td>16268.139244</td>\n",
 661 |        "    </tr>\n",
 662 |        "    <tr>\n",
 663 |        "      <th>1574252</th>\n",
 664 |        "      <td>1515368340</td>\n",
 665 |        "      <td>16268.14</td>\n",
 666 |        "      <td>16304.56</td>\n",
 667 |        "      <td>16268.14</td>\n",
 668 |        "      <td>16304.56</td>\n",
 669 |        "      <td>6.589334</td>\n",
 670 |        "      <td>107322.764440</td>\n",
 671 |        "      <td>16287.347440</td>\n",
 672 |        "    </tr>\n",
 673 |        "    <tr>\n",
 674 |        "      <th>1574253</th>\n",
 675 |        "      <td>1515368400</td>\n",
 676 |        "      <td>16304.56</td>\n",
 677 |        "      <td>16317.61</td>\n",
 678 |        "      <td>16304.55</td>\n",
 679 |        "      <td>16317.60</td>\n",
 680 |        "      <td>6.394264</td>\n",
 681 |        "      <td>104325.389320</td>\n",
 682 |        "      <td>16315.464663</td>\n",
 683 |        "    </tr>\n",
 684 |        "    <tr>\n",
 685 |        "      <th>1574254</th>\n",
 686 |        "      <td>1515368460</td>\n",
 687 |        "      <td>16317.61</td>\n",
 688 |        "      <td>16317.61</td>\n",
 689 |        "      <td>16317.60</td>\n",
 690 |        "      <td>16317.61</td>\n",
 691 |        "      <td>2.414222</td>\n",
 692 |        "      <td>39394.324203</td>\n",
 693 |        "      <td>16317.605795</td>\n",
 694 |        "    </tr>\n",
 695 |        "    <tr>\n",
 696 |        "      <th>1574255</th>\n",
 697 |        "      <td>1515368520</td>\n",
 698 |        "      <td>16317.61</td>\n",
 699 |        "      <td>16317.61</td>\n",
 700 |        "      <td>16270.00</td>\n",
 701 |        "      <td>16289.23</td>\n",
 702 |        "      <td>8.345635</td>\n",
 703 |        "      <td>136104.117340</td>\n",
 704 |        "      <td>16308.420256</td>\n",
 705 |        "    </tr>\n",
 706 |        "    <tr>\n",
 707 |        "      <th>1574256</th>\n",
 708 |        "      <td>1515368580</td>\n",
 709 |        "      <td>16289.23</td>\n",
 710 |        "      <td>16289.23</td>\n",
 711 |        "      <td>16269.89</td>\n",
 712 |        "      <td>16284.01</td>\n",
 713 |        "      <td>4.451807</td>\n",
 714 |        "      <td>72480.182488</td>\n",
 715 |        "      <td>16281.069515</td>\n",
 716 |        "    </tr>\n",
 717 |        "    <tr>\n",
 718 |        "      <th>1574257</th>\n",
 719 |        "      <td>1515368640</td>\n",
 720 |        "      <td>16284.01</td>\n",
 721 |        "      <td>16284.01</td>\n",
 722 |        "      <td>16275.00</td>\n",
 723 |        "      <td>16275.00</td>\n",
 724 |        "      <td>3.846284</td>\n",
 725 |        "      <td>62621.214930</td>\n",
 726 |        "      <td>16280.962987</td>\n",
 727 |        "    </tr>\n",
 728 |        "    <tr>\n",
 729 |        "      <th>1574258</th>\n",
 730 |        "      <td>1515368700</td>\n",
 731 |        "      <td>16275.00</td>\n",
 732 |        "      <td>16275.01</td>\n",
 733 |        "      <td>16268.00</td>\n",
 734 |        "      <td>16268.01</td>\n",
 735 |        "      <td>4.638978</td>\n",
 736 |        "      <td>75482.827940</td>\n",
 737 |        "      <td>16271.435615</td>\n",
 738 |        "    </tr>\n",
 739 |        "    <tr>\n",
 740 |        "      <th>1574259</th>\n",
 741 |        "      <td>1515368760</td>\n",
 742 |        "      <td>16268.01</td>\n",
 743 |        "      <td>16268.01</td>\n",
 744 |        "      <td>16268.00</td>\n",
 745 |        "      <td>16268.00</td>\n",
 746 |        "      <td>3.137728</td>\n",
 747 |        "      <td>51044.563061</td>\n",
 748 |        "      <td>16268.002143</td>\n",
 749 |        "    </tr>\n",
 750 |        "    <tr>\n",
 751 |        "      <th>1574260</th>\n",
 752 |        "      <td>1515368820</td>\n",
 753 |        "      <td>16268.00</td>\n",
 754 |        "      <td>16268.01</td>\n",
 755 |        "      <td>16232.04</td>\n",
 756 |        "      <td>16232.05</td>\n",
 757 |        "      <td>33.674919</td>\n",
 758 |        "      <td>547471.335260</td>\n",
 759 |        "      <td>16257.539597</td>\n",
 760 |        "    </tr>\n",
 761 |        "    <tr>\n",
 762 |        "      <th>1574261</th>\n",
 763 |        "      <td>1515368880</td>\n",
 764 |        "      <td>16232.04</td>\n",
 765 |        "      <td>16232.05</td>\n",
 766 |        "      <td>16203.61</td>\n",
 767 |        "      <td>16221.57</td>\n",
 768 |        "      <td>14.422389</td>\n",
 769 |        "      <td>233865.898850</td>\n",
 770 |        "      <td>16215.475284</td>\n",
 771 |        "    </tr>\n",
 772 |        "    <tr>\n",
 773 |        "      <th>1574262</th>\n",
 774 |        "      <td>1515368940</td>\n",
 775 |        "      <td>16221.01</td>\n",
 776 |        "      <td>16221.01</td>\n",
 777 |        "      <td>16220.00</td>\n",
 778 |        "      <td>16220.00</td>\n",
 779 |        "      <td>3.694251</td>\n",
 780 |        "      <td>59923.368690</td>\n",
 781 |        "      <td>16220.710150</td>\n",
 782 |        "    </tr>\n",
 783 |        "    <tr>\n",
 784 |        "      <th>1574263</th>\n",
 785 |        "      <td>1515369000</td>\n",
 786 |        "      <td>16220.01</td>\n",
 787 |        "      <td>16221.02</td>\n",
 788 |        "      <td>16201.00</td>\n",
 789 |        "      <td>16221.01</td>\n",
 790 |        "      <td>5.802667</td>\n",
 791 |        "      <td>94091.324231</td>\n",
 792 |        "      <td>16215.186394</td>\n",
 793 |        "    </tr>\n",
 794 |        "    <tr>\n",
 795 |        "      <th>1574264</th>\n",
 796 |        "      <td>1515369060</td>\n",
 797 |        "      <td>16221.01</td>\n",
 798 |        "      <td>16221.01</td>\n",
 799 |        "      <td>16200.69</td>\n",
 800 |        "      <td>16221.00</td>\n",
 801 |        "      <td>2.366366</td>\n",
 802 |        "      <td>38368.605933</td>\n",
 803 |        "      <td>16214.144086</td>\n",
 804 |        "    </tr>\n",
 805 |        "    <tr>\n",
 806 |        "      <th>1574265</th>\n",
 807 |        "      <td>1515369120</td>\n",
 808 |        "      <td>16221.01</td>\n",
 809 |        "      <td>16221.01</td>\n",
 810 |        "      <td>16172.21</td>\n",
 811 |        "      <td>16174.22</td>\n",
 812 |        "      <td>19.626989</td>\n",
 813 |        "      <td>317758.570910</td>\n",
 814 |        "      <td>16189.878976</td>\n",
 815 |        "    </tr>\n",
 816 |        "    <tr>\n",
 817 |        "      <th>1574266</th>\n",
 818 |        "      <td>1515369180</td>\n",
 819 |        "      <td>16174.22</td>\n",
 820 |        "      <td>16174.22</td>\n",
 821 |        "      <td>16174.21</td>\n",
 822 |        "      <td>16174.21</td>\n",
 823 |        "      <td>7.481674</td>\n",
 824 |        "      <td>121010.227010</td>\n",
 825 |        "      <td>16174.217319</td>\n",
 826 |        "    </tr>\n",
 827 |        "    <tr>\n",
 828 |        "      <th>1574267</th>\n",
 829 |        "      <td>1515369240</td>\n",
 830 |        "      <td>16174.22</td>\n",
 831 |        "      <td>16174.22</td>\n",
 832 |        "      <td>16174.21</td>\n",
 833 |        "      <td>16174.22</td>\n",
 834 |        "      <td>7.421392</td>\n",
 835 |        "      <td>120035.176120</td>\n",
 836 |        "      <td>16174.213396</td>\n",
 837 |        "    </tr>\n",
 838 |        "    <tr>\n",
 839 |        "      <th>1574268</th>\n",
 840 |        "      <td>1515369300</td>\n",
 841 |        "      <td>16174.21</td>\n",
 842 |        "      <td>16174.22</td>\n",
 843 |        "      <td>16174.21</td>\n",
 844 |        "      <td>16174.21</td>\n",
 845 |        "      <td>3.030103</td>\n",
 846 |        "      <td>49009.542468</td>\n",
 847 |        "      <td>16174.218650</td>\n",
 848 |        "    </tr>\n",
 849 |        "    <tr>\n",
 850 |        "      <th>1574269</th>\n",
 851 |        "      <td>1515369360</td>\n",
 852 |        "      <td>16174.21</td>\n",
 853 |        "      <td>16174.23</td>\n",
 854 |        "      <td>16174.21</td>\n",
 855 |        "      <td>16174.23</td>\n",
 856 |        "      <td>7.594119</td>\n",
 857 |        "      <td>122828.956770</td>\n",
 858 |        "      <td>16174.221301</td>\n",
 859 |        "    </tr>\n",
 860 |        "    <tr>\n",
 861 |        "      <th>1574270</th>\n",
 862 |        "      <td>1515369420</td>\n",
 863 |        "      <td>16174.23</td>\n",
 864 |        "      <td>16174.23</td>\n",
 865 |        "      <td>16174.21</td>\n",
 866 |        "      <td>16174.22</td>\n",
 867 |        "      <td>11.902468</td>\n",
 868 |        "      <td>192513.150940</td>\n",
 869 |        "      <td>16174.221081</td>\n",
 870 |        "    </tr>\n",
 871 |        "    <tr>\n",
 872 |        "      <th>1574271</th>\n",
 873 |        "      <td>1515369480</td>\n",
 874 |        "      <td>16174.22</td>\n",
 875 |        "      <td>16174.22</td>\n",
 876 |        "      <td>16174.21</td>\n",
 877 |        "      <td>16174.21</td>\n",
 878 |        "      <td>3.860840</td>\n",
 879 |        "      <td>62446.073684</td>\n",
 880 |        "      <td>16174.218136</td>\n",
 881 |        "    </tr>\n",
 882 |        "    <tr>\n",
 883 |        "      <th>1574272</th>\n",
 884 |        "      <td>1515369540</td>\n",
 885 |        "      <td>16174.22</td>\n",
 886 |        "      <td>16174.22</td>\n",
 887 |        "      <td>16174.21</td>\n",
 888 |        "      <td>16174.22</td>\n",
 889 |        "      <td>1.179093</td>\n",
 890 |        "      <td>19070.914509</td>\n",
 891 |        "      <td>16174.219514</td>\n",
 892 |        "    </tr>\n",
 893 |        "    <tr>\n",
 894 |        "      <th>1574273</th>\n",
 895 |        "      <td>1515369600</td>\n",
 896 |        "      <td>16174.22</td>\n",
 897 |        "      <td>16174.23</td>\n",
 898 |        "      <td>16174.22</td>\n",
 899 |        "      <td>16174.22</td>\n",
 900 |        "      <td>5.401224</td>\n",
 901 |        "      <td>87360.593222</td>\n",
 902 |        "      <td>16174.220219</td>\n",
 903 |        "    </tr>\n",
 904 |        "  </tbody>\n",
 905 |        "</table>\n",
 906 |        "<p>1574274 rows × 8 columns</p>\n",
 907 |        "</div>"
 908 |       ],
 909 |       "text/plain": [
 910 |        "          Timestamp      Open      High       Low     Close  Volume_(BTC)  \\\n",
 911 |        "0        1417411980    300.00    300.00    300.00    300.00      0.010000   \n",
 912 |        "1        1417412040    300.00    300.00    300.00    300.00      0.010000   \n",
 913 |        "2        1417412100    300.00    300.00    300.00    300.00      0.010000   \n",
 914 |        "3        1417412160    300.00    300.00    300.00    300.00      0.010000   \n",
 915 |        "4        1417412220    300.00    300.00    300.00    300.00      0.010000   \n",
 916 |        "5        1417412280    300.00    300.00    300.00    300.00      0.010000   \n",
 917 |        "6        1417412340    300.00    300.00    300.00    300.00      0.010000   \n",
 918 |        "7        1417412400    300.00    300.00    300.00    300.00      0.010000   \n",
 919 |        "8        1417412460    300.00    300.00    300.00    300.00      0.010000   \n",
 920 |        "9        1417412520    300.00    300.00    300.00    300.00      0.010000   \n",
 921 |        "10       1417412580    300.00    300.00    300.00    300.00      0.010000   \n",
 922 |        "11       1417412640    300.00    300.00    300.00    300.00      0.010000   \n",
 923 |        "12       1417412700    300.00    300.00    300.00    300.00      0.010000   \n",
 924 |        "13       1417412760    300.00    300.00    300.00    300.00      0.010000   \n",
 925 |        "14       1417412820    300.00    300.00    300.00    300.00      0.010000   \n",
 926 |        "15       1417412880    300.00    300.00    300.00    300.00      0.010000   \n",
 927 |        "16       1417412940    300.00    300.00    300.00    300.00      0.010000   \n",
 928 |        "17       1417413000    300.00    300.00    300.00    300.00      0.010000   \n",
 929 |        "18       1417413060    300.00    300.00    300.00    300.00      0.010000   \n",
 930 |        "19       1417413120    300.00    300.00    300.00    300.00      0.010000   \n",
 931 |        "20       1417413180    300.00    300.00    300.00    300.00      0.010000   \n",
 932 |        "21       1417413240    300.00    300.00    300.00    300.00      0.010000   \n",
 933 |        "22       1417413300    300.00    300.00    300.00    300.00      0.010000   \n",
 934 |        "23       1417413360    300.00    300.00    300.00    300.00      0.010000   \n",
 935 |        "24       1417413420    300.00    300.00    300.00    300.00      0.010000   \n",
 936 |        "25       1417413480    300.00    300.00    300.00    300.00      0.010000   \n",
 937 |        "26       1417413540    300.00    300.00    300.00    300.00      0.010000   \n",
 938 |        "27       1417413600    300.00    300.00    300.00    300.00      0.010000   \n",
 939 |        "28       1417413660    300.00    300.00    300.00    300.00      0.010000   \n",
 940 |        "29       1417413720    300.00    300.00    300.00    300.00      0.010000   \n",
 941 |        "...             ...       ...       ...       ...       ...           ...   \n",
 942 |        "1574244  1515367860  16329.79  16349.00  16329.79  16349.00      2.364011   \n",
 943 |        "1574245  1515367920  16349.00  16349.00  16329.00  16329.00      4.303270   \n",
 944 |        "1574246  1515367980  16329.01  16329.01  16300.00  16302.85      8.183248   \n",
 945 |        "1574247  1515368040  16302.84  16302.84  16279.74  16279.74      7.083056   \n",
 946 |        "1574248  1515368100  16279.75  16279.76  16266.06  16266.06      8.379655   \n",
 947 |        "1574249  1515368160  16266.07  16266.07  16266.06  16266.06      4.943145   \n",
 948 |        "1574250  1515368220  16266.06  16268.24  16266.06  16268.14      1.764196   \n",
 949 |        "1574251  1515368280  16268.13  16268.14  16268.13  16268.14      1.207304   \n",
 950 |        "1574252  1515368340  16268.14  16304.56  16268.14  16304.56      6.589334   \n",
 951 |        "1574253  1515368400  16304.56  16317.61  16304.55  16317.60      6.394264   \n",
 952 |        "1574254  1515368460  16317.61  16317.61  16317.60  16317.61      2.414222   \n",
 953 |        "1574255  1515368520  16317.61  16317.61  16270.00  16289.23      8.345635   \n",
 954 |        "1574256  1515368580  16289.23  16289.23  16269.89  16284.01      4.451807   \n",
 955 |        "1574257  1515368640  16284.01  16284.01  16275.00  16275.00      3.846284   \n",
 956 |        "1574258  1515368700  16275.00  16275.01  16268.00  16268.01      4.638978   \n",
 957 |        "1574259  1515368760  16268.01  16268.01  16268.00  16268.00      3.137728   \n",
 958 |        "1574260  1515368820  16268.00  16268.01  16232.04  16232.05     33.674919   \n",
 959 |        "1574261  1515368880  16232.04  16232.05  16203.61  16221.57     14.422389   \n",
 960 |        "1574262  1515368940  16221.01  16221.01  16220.00  16220.00      3.694251   \n",
 961 |        "1574263  1515369000  16220.01  16221.02  16201.00  16221.01      5.802667   \n",
 962 |        "1574264  1515369060  16221.01  16221.01  16200.69  16221.00      2.366366   \n",
 963 |        "1574265  1515369120  16221.01  16221.01  16172.21  16174.22     19.626989   \n",
 964 |        "1574266  1515369180  16174.22  16174.22  16174.21  16174.21      7.481674   \n",
 965 |        "1574267  1515369240  16174.22  16174.22  16174.21  16174.22      7.421392   \n",
 966 |        "1574268  1515369300  16174.21  16174.22  16174.21  16174.21      3.030103   \n",
 967 |        "1574269  1515369360  16174.21  16174.23  16174.21  16174.23      7.594119   \n",
 968 |        "1574270  1515369420  16174.23  16174.23  16174.21  16174.22     11.902468   \n",
 969 |        "1574271  1515369480  16174.22  16174.22  16174.21  16174.21      3.860840   \n",
 970 |        "1574272  1515369540  16174.22  16174.22  16174.21  16174.22      1.179093   \n",
 971 |        "1574273  1515369600  16174.22  16174.23  16174.22  16174.22      5.401224   \n",
 972 |        "\n",
 973 |        "         Volume_(Currency)  Weighted_Price  \n",
 974 |        "0                 3.000000      300.000000  \n",
 975 |        "1                 3.000000      300.000000  \n",
 976 |        "2                 3.000000      300.000000  \n",
 977 |        "3                 3.000000      300.000000  \n",
 978 |        "4                 3.000000      300.000000  \n",
 979 |        "5                 3.000000      300.000000  \n",
 980 |        "6                 3.000000      300.000000  \n",
 981 |        "7                 3.000000      300.000000  \n",
 982 |        "8                 3.000000      300.000000  \n",
 983 |        "9                 3.000000      300.000000  \n",
 984 |        "10                3.000000      300.000000  \n",
 985 |        "11                3.000000      300.000000  \n",
 986 |        "12                3.000000      300.000000  \n",
 987 |        "13                3.000000      300.000000  \n",
 988 |        "14                3.000000      300.000000  \n",
 989 |        "15                3.000000      300.000000  \n",
 990 |        "16                3.000000      300.000000  \n",
 991 |        "17                3.000000      300.000000  \n",
 992 |        "18                3.000000      300.000000  \n",
 993 |        "19                3.000000      300.000000  \n",
 994 |        "20                3.000000      300.000000  \n",
 995 |        "21                3.000000      300.000000  \n",
 996 |        "22                3.000000      300.000000  \n",
 997 |        "23                3.000000      300.000000  \n",
 998 |        "24                3.000000      300.000000  \n",
 999 |        "25                3.000000      300.000000  \n",
1000 |        "26                3.000000      300.000000  \n",
1001 |        "27                3.000000      300.000000  \n",
1002 |        "28                3.000000      300.000000  \n",
1003 |        "29                3.000000      300.000000  \n",
1004 |        "...                    ...             ...  \n",
1005 |        "1574244       38642.637918    16346.218304  \n",
1006 |        "1574245       70338.446619    16345.349090  \n",
1007 |        "1574246      133574.283340    16322.892267  \n",
1008 |        "1574247      115426.384420    16296.128527  \n",
1009 |        "1574248      136373.204380    16274.321438  \n",
1010 |        "1574249       80405.530720    16266.068487  \n",
1011 |        "1574250       28698.189067    16267.005559  \n",
1012 |        "1574251       19640.595763    16268.139244  \n",
1013 |        "1574252      107322.764440    16287.347440  \n",
1014 |        "1574253      104325.389320    16315.464663  \n",
1015 |        "1574254       39394.324203    16317.605795  \n",
1016 |        "1574255      136104.117340    16308.420256  \n",
1017 |        "1574256       72480.182488    16281.069515  \n",
1018 |        "1574257       62621.214930    16280.962987  \n",
1019 |        "1574258       75482.827940    16271.435615  \n",
1020 |        "1574259       51044.563061    16268.002143  \n",
1021 |        "1574260      547471.335260    16257.539597  \n",
1022 |        "1574261      233865.898850    16215.475284  \n",
1023 |        "1574262       59923.368690    16220.710150  \n",
1024 |        "1574263       94091.324231    16215.186394  \n",
1025 |        "1574264       38368.605933    16214.144086  \n",
1026 |        "1574265      317758.570910    16189.878976  \n",
1027 |        "1574266      121010.227010    16174.217319  \n",
1028 |        "1574267      120035.176120    16174.213396  \n",
1029 |        "1574268       49009.542468    16174.218650  \n",
1030 |        "1574269      122828.956770    16174.221301  \n",
1031 |        "1574270      192513.150940    16174.221081  \n",
1032 |        "1574271       62446.073684    16174.218136  \n",
1033 |        "1574272       19070.914509    16174.219514  \n",
1034 |        "1574273       87360.593222    16174.220219  \n",
1035 |        "\n",
1036 |        "[1574274 rows x 8 columns]"
1037 |       ]
1038 |      },
1039 |      "execution_count": 8,
1040 |      "metadata": {},
1041 |      "output_type": "execute_result"
1042 |     }
1043 |    ],
1044 |    "source": [
1045 |     "bit_df"
1046 |    ]
1047 |   },
1048 |   {
1049 |    "cell_type": "code",
1050 |    "execution_count": 11,
1051 |    "metadata": {},
1052 |    "outputs": [
1053 |     {
1054 |      "data": {
1055 |       "text/plain": [
1056 |        "Timestamp              int64\n",
1057 |        "Open                 float64\n",
1058 |        "High                 float64\n",
1059 |        "Low                  float64\n",
1060 |        "Close                float64\n",
1061 |        "Volume_(BTC)         float64\n",
1062 |        "Volume_(Currency)    float64\n",
1063 |        "Weighted_Price       float64\n",
1064 |        "dtype: object"
1065 |       ]
1066 |      },
1067 |      "execution_count": 11,
1068 |      "metadata": {},
1069 |      "output_type": "execute_result"
1070 |     }
1071 |    ],
1072 |    "source": [
1073 |     "bit_df.dtypes"
1074 |    ]
1075 |   },
1076 |   {
1077 |    "cell_type": "code",
1078 |    "execution_count": 12,
1079 |    "metadata": {},
1080 |    "outputs": [
1081 |     {
1082 |      "data": {
1083 |       "text/plain": [
1084 |        "0         2014-12-01 05:33:00\n",
1085 |        "1         2014-12-01 05:34:00\n",
1086 |        "2         2014-12-01 05:35:00\n",
1087 |        "3         2014-12-01 05:36:00\n",
1088 |        "4         2014-12-01 05:37:00\n",
1089 |        "5         2014-12-01 05:38:00\n",
1090 |        "6         2014-12-01 05:39:00\n",
1091 |        "7         2014-12-01 05:40:00\n",
1092 |        "8         2014-12-01 05:41:00\n",
1093 |        "9         2014-12-01 05:42:00\n",
1094 |        "10        2014-12-01 05:43:00\n",
1095 |        "11        2014-12-01 05:44:00\n",
1096 |        "12        2014-12-01 05:45:00\n",
1097 |        "13        2014-12-01 05:46:00\n",
1098 |        "14        2014-12-01 05:47:00\n",
1099 |        "15        2014-12-01 05:48:00\n",
1100 |        "16        2014-12-01 05:49:00\n",
1101 |        "17        2014-12-01 05:50:00\n",
1102 |        "18        2014-12-01 05:51:00\n",
1103 |        "19        2014-12-01 05:52:00\n",
1104 |        "20        2014-12-01 05:53:00\n",
1105 |        "21        2014-12-01 05:54:00\n",
1106 |        "22        2014-12-01 05:55:00\n",
1107 |        "23        2014-12-01 05:56:00\n",
1108 |        "24        2014-12-01 05:57:00\n",
1109 |        "25        2014-12-01 05:58:00\n",
1110 |        "26        2014-12-01 05:59:00\n",
1111 |        "27        2014-12-01 06:00:00\n",
1112 |        "28        2014-12-01 06:01:00\n",
1113 |        "29        2014-12-01 06:02:00\n",
1114 |        "                  ...        \n",
1115 |        "1574244   2018-01-07 23:31:00\n",
1116 |        "1574245   2018-01-07 23:32:00\n",
1117 |        "1574246   2018-01-07 23:33:00\n",
1118 |        "1574247   2018-01-07 23:34:00\n",
1119 |        "1574248   2018-01-07 23:35:00\n",
1120 |        "1574249   2018-01-07 23:36:00\n",
1121 |        "1574250   2018-01-07 23:37:00\n",
1122 |        "1574251   2018-01-07 23:38:00\n",
1123 |        "1574252   2018-01-07 23:39:00\n",
1124 |        "1574253   2018-01-07 23:40:00\n",
1125 |        "1574254   2018-01-07 23:41:00\n",
1126 |        "1574255   2018-01-07 23:42:00\n",
1127 |        "1574256   2018-01-07 23:43:00\n",
1128 |        "1574257   2018-01-07 23:44:00\n",
1129 |        "1574258   2018-01-07 23:45:00\n",
1130 |        "1574259   2018-01-07 23:46:00\n",
1131 |        "1574260   2018-01-07 23:47:00\n",
1132 |        "1574261   2018-01-07 23:48:00\n",
1133 |        "1574262   2018-01-07 23:49:00\n",
1134 |        "1574263   2018-01-07 23:50:00\n",
1135 |        "1574264   2018-01-07 23:51:00\n",
1136 |        "1574265   2018-01-07 23:52:00\n",
1137 |        "1574266   2018-01-07 23:53:00\n",
1138 |        "1574267   2018-01-07 23:54:00\n",
1139 |        "1574268   2018-01-07 23:55:00\n",
1140 |        "1574269   2018-01-07 23:56:00\n",
1141 |        "1574270   2018-01-07 23:57:00\n",
1142 |        "1574271   2018-01-07 23:58:00\n",
1143 |        "1574272   2018-01-07 23:59:00\n",
1144 |        "1574273   2018-01-08 00:00:00\n",
1145 |        "Name: Timestamp, Length: 1574274, dtype: datetime64[ns]"
1146 |       ]
1147 |      },
1148 |      "execution_count": 12,
1149 |      "metadata": {},
1150 |      "output_type": "execute_result"
1151 |     }
1152 |    ],
1153 |    "source": [
1154 |     "pd.to_datetime(bit_df.Timestamp, unit='s')"
1155 |    ]
1156 |   },
1157 |   {
1158 |    "cell_type": "markdown",
1159 |    "metadata": {},
1160 |    "source": [
1161 |     "## Random Forest"
1162 |    ]
1163 |   },
1164 |   {
1165 |    "cell_type": "code",
1166 |    "execution_count": 33,
1167 |    "metadata": {},
1168 |    "outputs": [],
1169 |    "source": [
1170 |     "ignore = {'buy'}\n",
1171 |     "cols = [c for c in bit_df.columns if c not in ignore]\n",
1172 |     "X = bit_df[cols]\n",
1173 |     "y = bit_df.buy\n",
1174 |     "X_train, X_test, y_train, y_test = model_selection.\\\n",
1175 |     "    train_test_split(X, y, test_size=.3, random_state=42)\n"
1176 |    ]
1177 |   },
1178 |   {
1179 |    "cell_type": "code",
1180 |    "execution_count": 50,
1181 |    "metadata": {},
1182 |    "outputs": [
1183 |     {
1184 |      "data": {
1185 |       "text/plain": [
1186 |        "0.49666666666666665"
1187 |       ]
1188 |      },
1189 |      "execution_count": 50,
1190 |      "metadata": {},
1191 |      "output_type": "execute_result"
1192 |     }
1193 |    ],
1194 |    "source": [
1195 |     "rf1 = ensemble.RandomForestClassifier(random_state=42)\n",
1196 |     "rf1.fit(X_train, y_train)\n",
1197 |     "rf1.score(X_test, y_test)"
1198 |    ]
1199 |   },
1200 |   {
1201 |    "cell_type": "code",
1202 |    "execution_count": 37,
1203 |    "metadata": {},
1204 |    "outputs": [
1205 |     {
1206 |      "data": {
1207 |       "text/plain": [
1208 |        "0.977110157367668"
1209 |       ]
1210 |      },
1211 |      "execution_count": 37,
1212 |      "metadata": {},
1213 |      "output_type": "execute_result"
1214 |     }
1215 |    ],
1216 |    "source": [
1217 |     "rf1.score(X_train, y_train)"
1218 |    ]
1219 |   },
1220 |   {
1221 |    "cell_type": "markdown",
1222 |    "metadata": {},
1223 |    "source": [
1224 |     "## ROC Curve"
1225 |    ]
1226 |   },
1227 |   {
1228 |    "cell_type": "code",
1229 |    "execution_count": 40,
1230 |    "metadata": {},
1231 |    "outputs": [
1232 |     {
1233 |      "data": {
1234 |       "image/png": "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\n",
1235 |       "text/plain": [
1236 |        "<matplotlib.figure.Figure at 0x11a431a58>"
1237 |       ]
1238 |      },
1239 |      "metadata": {},
1240 |      "output_type": "display_data"
1241 |     }
1242 |    ],
1243 |    "source": [
1244 |     "# yellowbrick version\n",
1245 |     "fig, ax = plt.subplots(figsize=(10, 10))\n",
1246 |     "roc_viz = ROCAUC(rf1)\n",
1247 |     "roc_viz.score(X_test, y_test)\n",
1248 |     "#roc_viz.score(X_train, y_train)\n",
1249 |     "\n",
1250 |     "roc_viz.poof()"
1251 |    ]
1252 |   },
1253 |   {
1254 |    "cell_type": "code",
1255 |    "execution_count": 31,
1256 |    "metadata": {},
1257 |    "outputs": [
1258 |     {
1259 |      "data": {
1260 |       "text/plain": [
1261 |        "date\n",
1262 |        "2015-04-15    1\n",
1263 |        "2015-04-16    0\n",
1264 |        "2015-04-17    1\n",
1265 |        "2015-04-18    1\n",
1266 |        "2015-04-19    1\n",
1267 |        "2015-04-20    1\n",
1268 |        "2015-04-21    0\n",
1269 |        "2015-04-22    1\n",
1270 |        "2015-04-23    0\n",
1271 |        "2015-04-24    0\n",
1272 |        "2015-04-25    0\n",
1273 |        "2015-04-26    1\n",
1274 |        "2015-04-27    0\n",
1275 |        "2015-04-28    0\n",
1276 |        "2015-04-29    1\n",
1277 |        "2015-04-30    0\n",
1278 |        "2015-05-01    1\n",
1279 |        "2015-05-02    1\n",
1280 |        "2015-05-03    0\n",
1281 |        "2015-05-04    0\n",
1282 |        "2015-05-05    0\n",
1283 |        "2015-05-06    1\n",
1284 |        "2015-05-07    1\n",
1285 |        "2015-05-08    0\n",
1286 |        "2015-05-09    0\n",
1287 |        "2015-05-10    1\n",
1288 |        "2015-05-11    0\n",
1289 |        "2015-05-12    0\n",
1290 |        "2015-05-13    1\n",
1291 |        "2015-05-14    1\n",
1292 |        "             ..\n",
1293 |        "2017-12-09    0\n",
1294 |        "2017-12-10    1\n",
1295 |        "2017-12-11    1\n",
1296 |        "2017-12-12    0\n",
1297 |        "2017-12-13    1\n",
1298 |        "2017-12-14    1\n",
1299 |        "2017-12-15    1\n",
1300 |        "2017-12-16    0\n",
1301 |        "2017-12-17    0\n",
1302 |        "2017-12-18    0\n",
1303 |        "2017-12-19    0\n",
1304 |        "2017-12-20    0\n",
1305 |        "2017-12-21    0\n",
1306 |        "2017-12-22    1\n",
1307 |        "2017-12-23    0\n",
1308 |        "2017-12-24    0\n",
1309 |        "2017-12-25    1\n",
1310 |        "2017-12-26    0\n",
1311 |        "2017-12-27    0\n",
1312 |        "2017-12-28    1\n",
1313 |        "2017-12-29    0\n",
1314 |        "2017-12-30    1\n",
1315 |        "2017-12-31    0\n",
1316 |        "2018-01-01    1\n",
1317 |        "2018-01-02    1\n",
1318 |        "2018-01-03    1\n",
1319 |        "2018-01-04    1\n",
1320 |        "2018-01-05    1\n",
1321 |        "2018-01-06    0\n",
1322 |        "2018-01-07    0\n",
1323 |        "Freq: D, Name: buy, Length: 999, dtype: int64"
1324 |       ]
1325 |      },
1326 |      "execution_count": 31,
1327 |      "metadata": {},
1328 |      "output_type": "execute_result"
1329 |     }
1330 |    ],
1331 |    "source": [
1332 |     "\n"
1333 |    ]
1334 |   },
1335 |   {
1336 |    "cell_type": "code",
1337 |    "execution_count": null,
1338 |    "metadata": {},
1339 |    "outputs": [],
1340 |    "source": []
1341 |   }
1342 |  ],
1343 |  "metadata": {
1344 |   "kernelspec": {
1345 |    "display_name": "Python 3",
1346 |    "language": "python",
1347 |    "name": "python3"
1348 |   },
1349 |   "language_info": {
1350 |    "codemirror_mode": {
1351 |     "name": "ipython",
1352 |     "version": 3
1353 |    },
1354 |    "file_extension": ".py",
1355 |    "mimetype": "text/x-python",
1356 |    "name": "python",
1357 |    "nbconvert_exporter": "python",
1358 |    "pygments_lexer": "ipython3",
1359 |    "version": "3.6.4"
1360 |   }
1361 |  },
1362 |  "nbformat": 4,
1363 |  "nbformat_minor": 2
1364 | }
1365 | 


--------------------------------------------------------------------------------