PyPI - cryptodatapy - Versions diffs - 0.2.4__py3-none-any.whl → 0.2.5__py3-none-any.whl - Mend

cryptodatapy 0.2.4py3-none-any.whl → 0.2.5py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (9) hide show

cryptodatapy/transform/clean_perp_futures_ohlcv.ipynb CHANGED Viewed

@@ -64,6 +64,27 @@
   {
    "cell_type": "code",
    "execution_count": 4,
+   "id": "5e796745",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "'BTCST/USDT:USDT' in perp_tickers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "id": "fcb74458",
    "metadata": {},
    "outputs": [],
@@ -75,7 +96,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
+   "id": "4b86fa0d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "'BTCST/USDT:USDT' in spot_tickers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
    "id": "7962f7e5",
    "metadata": {},
    "outputs": [],
@@ -86,7 +128,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "id": "877811c1",
    "metadata": {},
    "outputs": [
@@ -96,7 +138,7 @@
        "314"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -108,7 +150,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
+   "id": "4ef7a85b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "'BTCST/USDT:USDT' in binance_tickers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
    "id": "fe425163",
    "metadata": {},
    "outputs": [],
@@ -120,7 +183,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 11,
+   "id": "9c63cd43",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "'BTCST' in cc_tickers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
    "id": "165053db",
    "metadata": {},
    "outputs": [],
@@ -128,24 +212,66 @@
     "# keep only USDT ticker\n",
     "bin_tickers = []\n",
     "for ticker in binance_tickers:\n",
-    "    if '/' in ticker and ticker.split('/')[1] == 'USDT':\n",
+    "    if '/' in ticker and ticker.split('/')[1] == 'USDT:USDT':\n",
     "        bin_tickers.append(ticker.split('/')[0])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 13,
+   "id": "c93e487a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "'BTCST' in bin_tickers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
    "id": "d6cf8a4c",
    "metadata": {},
    "outputs": [],
    "source": [
     "# usdt tickers\n",
-    "usdt_tickers = [ticker.split('/')[0] for ticker in binance_tickers if '/'in ticker and ticker.split('/')[1] == 'USDT']"
+    "usdt_tickers = [ticker.split('/')[0] for ticker in binance_tickers if '/'in ticker and ticker.split('/')[1] == 'USDT:USDT']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 15,
+   "id": "11ec0e6d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "282"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(usdt_tickers)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
    "id": "633f7a3e",
    "metadata": {},
    "outputs": [],
@@ -156,17 +282,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 17,
    "id": "30337a71",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "0"
+       "270"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -175,6 +301,27 @@
     "len(tickers)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "7bb3b25f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "'BTCST' in tickers"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "f80eb97d",
@@ -185,7 +332,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 20,
    "id": "49b09508",
    "metadata": {},
    "outputs": [],
@@ -200,29 +347,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 21,
    "id": "6ac9365b",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "# df1 = GetData(data_req).get_series()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "98a425b2",
-   "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING:root:Failed to get ohlcv data for BTCST/USDT.\n",
+      "WARNING:root:binanceusdm {\"code\":-1122,\"msg\":\"Invalid symbol status.\"}\n",
+      "WARNING:root:Failed to pull data on attempt #1.\n",
+      "WARNING:root:Failed to get ohlcv data for BTCST/USDT.\n",
+      "WARNING:root:binanceusdm {\"code\":-1122,\"msg\":\"Invalid symbol status.\"}\n",
+      "WARNING:root:Failed to pull data on attempt #2.\n",
+      "WARNING:root:Failed to get ohlcv data for BTCST/USDT.\n",
+      "WARNING:root:binanceusdm {\"code\":-1122,\"msg\":\"Invalid symbol status.\"}\n",
+      "WARNING:root:Failed to pull data on attempt #3.\n",
+      "WARNING:root:Failed to get OHLCV data from binanceusdm for BTCST/USDT after many attempts.\n"
+     ]
+    }
+   ],
    "source": [
-    "# df1.to_csv('binance_perp_futures.csv')\n",
-    "df1 = pd.read_csv('../../../../factorlab/notebooks/binance_perp_futures.csv', index_col=['date', 'ticker'], parse_dates=['date'])"
+    "df1 = GetData(data_req).get_series()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
-   "id": "0e04da4a",
+   "execution_count": 22,
+   "id": "364bb46e",
    "metadata": {},
    "outputs": [
     {
@@ -269,12 +422,12 @@
        "    <tr>\n",
        "      <th>2019-09-08</th>\n",
        "      <th>BTC</th>\n",
-       "      <td>10000.00</td>\n",
+       "      <td>10000.0</td>\n",
        "      <td>10412.65</td>\n",
-       "      <td>10000.00</td>\n",
+       "      <td>10000.0</td>\n",
        "      <td>10391.63</td>\n",
        "      <td>3096.291</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2019-09-09</th>\n",
@@ -282,14 +435,14 @@
        "      <td>10316.62</td>\n",
        "      <td>10475.54</td>\n",
        "      <td>10077.22</td>\n",
-       "      <td>10307.00</td>\n",
+       "      <td>10307.0</td>\n",
        "      <td>14824.373</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2019-09-10</th>\n",
        "      <th>BTC</th>\n",
-       "      <td>10307.00</td>\n",
+       "      <td>10307.0</td>\n",
        "      <td>10382.97</td>\n",
        "      <td>9940.87</td>\n",
        "      <td>10102.02</td>\n",
@@ -316,84 +469,123 @@
        "      <td>15609.634</td>\n",
        "      <td>0.0003</td>\n",
        "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th rowspan=\"5\" valign=\"top\">2024-08-13</th>\n",
+       "      <th>ZETA</th>\n",
+       "      <td>0.6558</td>\n",
+       "      <td>0.7099</td>\n",
+       "      <td>0.6143</td>\n",
+       "      <td>0.6556</td>\n",
+       "      <td>290931468.0</td>\n",
+       "      <td>-0.001465</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZIL</th>\n",
+       "      <td>0.01394</td>\n",
+       "      <td>0.01397</td>\n",
+       "      <td>0.01348</td>\n",
+       "      <td>0.01372</td>\n",
+       "      <td>211016383.0</td>\n",
+       "      <td>0.0002</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZK</th>\n",
+       "      <td>0.11683</td>\n",
+       "      <td>0.11895</td>\n",
+       "      <td>0.11223</td>\n",
+       "      <td>0.11713</td>\n",
+       "      <td>180118593.0</td>\n",
+       "      <td>0.0002</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZRO</th>\n",
+       "      <td>3.509</td>\n",
+       "      <td>3.533</td>\n",
+       "      <td>3.349</td>\n",
+       "      <td>3.459</td>\n",
+       "      <td>10802271.5</td>\n",
+       "      <td>0.000173</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZRX</th>\n",
+       "      <td>0.3102</td>\n",
+       "      <td>0.3126</td>\n",
+       "      <td>0.3</td>\n",
+       "      <td>0.3083</td>\n",
+       "      <td>18072404.9</td>\n",
+       "      <td>-0.000044</td>\n",
+       "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
+       "<p>222221 rows × 6 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "                       open      high       low     close     volume  \\\n",
-       "date       ticker                                                      \n",
-       "2019-09-08 BTC     10000.00  10412.65  10000.00  10391.63   3096.291   \n",
-       "2019-09-09 BTC     10316.62  10475.54  10077.22  10307.00  14824.373   \n",
-       "2019-09-10 BTC     10307.00  10382.97   9940.87  10102.02   9068.955   \n",
-       "2019-09-11 BTC     10094.27  10293.11   9884.31  10159.55  10897.922   \n",
-       "2019-09-12 BTC     10163.06  10450.13  10042.12  10415.13  15609.634   \n",
+       "                       open      high       low     close       volume  \\\n",
+       "date       ticker                                                        \n",
+       "2019-09-08 BTC      10000.0  10412.65   10000.0  10391.63     3096.291   \n",
+       "2019-09-09 BTC     10316.62  10475.54  10077.22   10307.0    14824.373   \n",
+       "2019-09-10 BTC      10307.0  10382.97   9940.87  10102.02     9068.955   \n",
+       "2019-09-11 BTC     10094.27  10293.11   9884.31  10159.55    10897.922   \n",
+       "2019-09-12 BTC     10163.06  10450.13  10042.12  10415.13    15609.634   \n",
+       "...                     ...       ...       ...       ...          ...   \n",
+       "2024-08-13 ZETA      0.6558    0.7099    0.6143    0.6556  290931468.0   \n",
+       "           ZIL      0.01394   0.01397   0.01348   0.01372  211016383.0   \n",
+       "           ZK       0.11683   0.11895   0.11223   0.11713  180118593.0   \n",
+       "           ZRO        3.509     3.533     3.349     3.459   10802271.5   \n",
+       "           ZRX       0.3102    0.3126       0.3    0.3083   18072404.9   \n",
        "\n",
        "                   funding_rate  \n",
        "date       ticker                \n",
-       "2019-09-08 BTC              NaN  \n",
-       "2019-09-09 BTC              NaN  \n",
+       "2019-09-08 BTC             <NA>  \n",
+       "2019-09-09 BTC             <NA>  \n",
        "2019-09-10 BTC           0.0002  \n",
        "2019-09-11 BTC           0.0003  \n",
-       "2019-09-12 BTC           0.0003  "
+       "2019-09-12 BTC           0.0003  \n",
+       "...                         ...  \n",
+       "2024-08-13 ZETA       -0.001465  \n",
+       "           ZIL           0.0002  \n",
+       "           ZK            0.0002  \n",
+       "           ZRO         0.000173  \n",
+       "           ZRX        -0.000044  \n",
+       "\n",
+       "[222221 rows x 6 columns]"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df1.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "32f15191",
-   "metadata": {},
-   "source": [
-    "### Binance Spot"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "83e9e466",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# pull OHLC from Binance\n",
-    "data_req = DataRequest(source='ccxt',\n",
-    "                       tickers=tickers, \n",
-    "                       fields=['open', 'high', 'low', 'close', 'volume'], \n",
-    "                       freq='d')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "82d4bbc7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# df2 = GetData(data_req).get_series()"
+    "df1"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
-   "id": "4f63eb21",
+   "execution_count": 23,
+   "id": "98a425b2",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# df2.to_csv('binance_spot.csv')\n",
-    "df2 = pd.read_csv('../../../../factorlab/notebooks/binance_spot.csv', index_col=['date', 'ticker'], parse_dates=['date'])"
+    "# df1.to_csv('binance_perp_futures.csv')\n",
+    "df1 = pd.read_csv('../../../../factorlab/notebooks/binance_perp_futures.csv', index_col=['date', 'ticker'], parse_dates=['date'])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
-   "id": "ce8929c1",
+   "execution_count": 24,
+   "id": "0e04da4a",
    "metadata": {},
    "outputs": [
     {
@@ -423,6 +615,7 @@
        "      <th>low</th>\n",
        "      <th>close</th>\n",
        "      <th>volume</th>\n",
+       "      <th>funding_rate</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>date</th>\n",
@@ -432,16 +625,202 @@
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
+       "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th rowspan=\"2\" valign=\"top\">2017-08-17</th>\n",
+       "      <th>2019-09-08</th>\n",
        "      <th>BTC</th>\n",
-       "      <td>4261.48</td>\n",
-       "      <td>4485.39</td>\n",
-       "      <td>4200.74</td>\n",
-       "      <td>4285.08</td>\n",
+       "      <td>10000.00</td>\n",
+       "      <td>10412.65</td>\n",
+       "      <td>10000.00</td>\n",
+       "      <td>10391.63</td>\n",
+       "      <td>3096.291</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2019-09-09</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>10316.62</td>\n",
+       "      <td>10475.54</td>\n",
+       "      <td>10077.22</td>\n",
+       "      <td>10307.00</td>\n",
+       "      <td>14824.373</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2019-09-10</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>10307.00</td>\n",
+       "      <td>10382.97</td>\n",
+       "      <td>9940.87</td>\n",
+       "      <td>10102.02</td>\n",
+       "      <td>9068.955</td>\n",
+       "      <td>0.0002</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2019-09-11</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>10094.27</td>\n",
+       "      <td>10293.11</td>\n",
+       "      <td>9884.31</td>\n",
+       "      <td>10159.55</td>\n",
+       "      <td>10897.922</td>\n",
+       "      <td>0.0003</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2019-09-12</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>10163.06</td>\n",
+       "      <td>10450.13</td>\n",
+       "      <td>10042.12</td>\n",
+       "      <td>10415.13</td>\n",
+       "      <td>15609.634</td>\n",
+       "      <td>0.0003</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       open      high       low     close     volume  \\\n",
+       "date       ticker                                                      \n",
+       "2019-09-08 BTC     10000.00  10412.65  10000.00  10391.63   3096.291   \n",
+       "2019-09-09 BTC     10316.62  10475.54  10077.22  10307.00  14824.373   \n",
+       "2019-09-10 BTC     10307.00  10382.97   9940.87  10102.02   9068.955   \n",
+       "2019-09-11 BTC     10094.27  10293.11   9884.31  10159.55  10897.922   \n",
+       "2019-09-12 BTC     10163.06  10450.13  10042.12  10415.13  15609.634   \n",
+       "\n",
+       "                   funding_rate  \n",
+       "date       ticker                \n",
+       "2019-09-08 BTC              NaN  \n",
+       "2019-09-09 BTC              NaN  \n",
+       "2019-09-10 BTC           0.0002  \n",
+       "2019-09-11 BTC           0.0003  \n",
+       "2019-09-12 BTC           0.0003  "
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df1.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "32f15191",
+   "metadata": {},
+   "source": [
+    "### Binance Spot"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "83e9e466",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# pull OHLC from Binance\n",
+    "data_req = DataRequest(source='ccxt',\n",
+    "                       tickers=tickers, \n",
+    "                       fields=['open', 'high', 'low', 'close', 'volume'], \n",
+    "                       freq='d')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "82d4bbc7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING:root:Missing recent OHLCV data for XMR/USDT.\n",
+      "WARNING:root:Missing recent OHLCV data for OMG/USDT.\n",
+      "WARNING:root:Missing recent OHLCV data for WAVES/USDT.\n",
+      "WARNING:root:Missing recent OHLCV data for OCEAN/USDT.\n",
+      "WARNING:root:Missing recent OHLCV data for XEM/USDT.\n",
+      "WARNING:root:Missing recent OHLCV data for BTCST/USDT.\n",
+      "WARNING:root:Missing recent OHLCV data for AGIX/USDT.\n",
+      "WARNING:root:Missing recent OHLCV data for BOND/USDT.\n",
+      "WARNING:root:Missing recent OHLCV data for BSV/USDT.\n"
+     ]
+    }
+   ],
+   "source": [
+    "df2 = GetData(data_req).get_series()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "4f63eb21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# df2.to_csv('binance_spot.csv')\n",
+    "df2 = pd.read_csv('../../../../factorlab/notebooks/binance_spot.csv', index_col=['date', 'ticker'], parse_dates=['date'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "ce8929c1",
+   "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></th>\n",
+       "      <th>open</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>close</th>\n",
+       "      <th>volume</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>date</th>\n",
+       "      <th>ticker</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th rowspan=\"2\" valign=\"top\">2017-08-17</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>4261.48</td>\n",
+       "      <td>4485.39</td>\n",
+       "      <td>4200.74</td>\n",
+       "      <td>4285.08</td>\n",
        "      <td>795.150377</td>\n",
        "    </tr>\n",
        "    <tr>\n",
@@ -492,7 +871,7 @@
        "2017-08-19 BTC     4108.37  4184.69  3850.00  4139.98   381.309763"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 28,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -511,7 +890,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 29,
    "id": "7f14d874",
    "metadata": {},
    "outputs": [],
@@ -525,17 +904,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 30,
    "id": "3a8708d3",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# df3 = GetData(data_req).get_series()"
+    "df3 = GetData(data_req).get_series()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 31,
    "id": "aa265538",
    "metadata": {},
    "outputs": [],
@@ -554,7 +933,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 32,
    "id": "f5ee4f6d",
    "metadata": {},
    "outputs": [],
@@ -565,7 +944,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 33,
    "id": "cbe07c91",
    "metadata": {},
    "outputs": [
@@ -674,7 +1053,7 @@
        "2010-07-21 BTC     0.07474  0.07921  0.06634  0.07921  575.00           0.0"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 33,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -685,7 +1064,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 34,
+   "id": "cef46007",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['BTC', 'LTC', 'DOGE', 'DASH', 'XLM', 'XMR', 'XRP', 'KEY', 'DGB', 'XEM',\n",
+       "       ...\n",
+       "       'TNSR', 'SAGA', 'REZ', 'BB', 'NOT', 'IO', 'ZK', 'LISTA', 'ZRO',\n",
+       "       'RENDER'],\n",
+       "      dtype='object', name='ticker', length=256)"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.index.get_level_values(1).unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "id": "d4c497d1",
    "metadata": {},
    "outputs": [],
@@ -696,74 +1100,98 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
-   "id": "a9b1764c",
+   "execution_count": 35,
+   "id": "9f8a899f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "clean = CleanData(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "29e1b955",
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Index(['AGIX', 'CTK', 'CVC', 'CVX', 'DGB', 'FTT', 'GLMR', 'IDEX', 'MDT',\n",
-      "       'OCEAN', 'RAD', 'RAY', 'SC', 'SLP', 'SNT', 'STPT', 'STRAX', 'WAVES'],\n",
-      "      dtype='object', name='ticker')\n"
-     ]
+     "data": {
+      "text/plain": [
+       "<cryptodatapy.transform.clean.CleanData at 0x7fb888103af0>"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "# clean data\n",
-    "clean_df = CleanData(df).filter_delisted_tickers().\\\n",
-    "                         filter_min_nobs(ts_obs=1500, cs_obs=10).\\\n",
-    "                         filter_outliers(od_method='mad', excl_cols=['volume', 'funding_rate'], thresh_val=10).\\\n",
-    "                         repair_outliers(imp_method='fcst').\\\n",
-    "                         filter_avg_trading_val(thresh_val=1000000).\\\n",
-    "                         filter_missing_vals_gaps().\\\n",
-    "                         get(attr='df').dropna(how='all')"
+    "clean.filter_delisted_tickers()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
-   "id": "3d423e53",
+   "execution_count": 37,
+   "id": "9315f178",
    "metadata": {},
    "outputs": [
     {
-     "ename": "KeyError",
-     "evalue": "'OCEAN'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/core/indexes/base.py:3800\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   3799\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 3800\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_engine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcasted_key\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   3801\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/_libs/index.pyx:138\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/_libs/index.pyx:165\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
-      "File \u001b[0;32mpandas/_libs/hashtable_class_helper.pxi:5745\u001b[0m, in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
-      "File \u001b[0;32mpandas/_libs/hashtable_class_helper.pxi:5753\u001b[0m, in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
-      "\u001b[0;31mKeyError\u001b[0m: 'OCEAN'",
-      "\nThe above exception was the direct cause of the following exception:\n",
-      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn [27], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m clean_df\u001b[38;5;241m.\u001b[39mloc[:, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mOCEAN\u001b[39m\u001b[38;5;124m'\u001b[39m, :]\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/core/indexing.py:1068\u001b[0m, in \u001b[0;36m_LocationIndexer.__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   1066\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_is_scalar_access(key):\n\u001b[1;32m   1067\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mobj\u001b[38;5;241m.\u001b[39m_get_value(\u001b[38;5;241m*\u001b[39mkey, takeable\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_takeable)\n\u001b[0;32m-> 1068\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_getitem_tuple\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1069\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1070\u001b[0m     \u001b[38;5;66;03m# we by definition only have the 0th axis\u001b[39;00m\n\u001b[1;32m   1071\u001b[0m     axis \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxis \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;241m0\u001b[39m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/core/indexing.py:1248\u001b[0m, in \u001b[0;36m_LocIndexer._getitem_tuple\u001b[0;34m(self, tup)\u001b[0m\n\u001b[1;32m   1246\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m suppress(IndexingError):\n\u001b[1;32m   1247\u001b[0m     tup \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_expand_ellipsis(tup)\n\u001b[0;32m-> 1248\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_getitem_lowerdim\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtup\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1250\u001b[0m \u001b[38;5;66;03m# no multi-index, so validate all of the indexers\u001b[39;00m\n\u001b[1;32m   1251\u001b[0m tup \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_tuple_indexer(tup)\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/core/indexing.py:942\u001b[0m, in \u001b[0;36m_LocationIndexer._getitem_lowerdim\u001b[0;34m(self, tup)\u001b[0m\n\u001b[1;32m    940\u001b[0m \u001b[38;5;66;03m# we may have a nested tuples indexer here\u001b[39;00m\n\u001b[1;32m    941\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_is_nested_tuple_indexer(tup):\n\u001b[0;32m--> 942\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_getitem_nested_tuple\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtup\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    944\u001b[0m \u001b[38;5;66;03m# we maybe be using a tuple to represent multiple dimensions here\u001b[39;00m\n\u001b[1;32m    945\u001b[0m ax0 \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mobj\u001b[38;5;241m.\u001b[39m_get_axis(\u001b[38;5;241m0\u001b[39m)\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/core/indexing.py:1034\u001b[0m, in \u001b[0;36m_LocationIndexer._getitem_nested_tuple\u001b[0;34m(self, tup)\u001b[0m\n\u001b[1;32m   1031\u001b[0m     \u001b[38;5;66;03m# this is a series with a multi-index specified a tuple of\u001b[39;00m\n\u001b[1;32m   1032\u001b[0m     \u001b[38;5;66;03m# selectors\u001b[39;00m\n\u001b[1;32m   1033\u001b[0m     axis \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxis \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;241m0\u001b[39m\n\u001b[0;32m-> 1034\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_getitem_axis\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtup\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1036\u001b[0m \u001b[38;5;66;03m# handle the multi-axis by taking sections and reducing\u001b[39;00m\n\u001b[1;32m   1037\u001b[0m \u001b[38;5;66;03m# this is iterative\u001b[39;00m\n\u001b[1;32m   1038\u001b[0m obj \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mobj\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/core/indexing.py:1306\u001b[0m, in \u001b[0;36m_LocIndexer._getitem_axis\u001b[0;34m(self, key, axis)\u001b[0m\n\u001b[1;32m   1304\u001b[0m \u001b[38;5;66;03m# nested tuple slicing\u001b[39;00m\n\u001b[1;32m   1305\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_nested_tuple(key, labels):\n\u001b[0;32m-> 1306\u001b[0m     locs \u001b[38;5;241m=\u001b[39m \u001b[43mlabels\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_locs\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1307\u001b[0m     indexer \u001b[38;5;241m=\u001b[39m [\u001b[38;5;28mslice\u001b[39m(\u001b[38;5;28;01mNone\u001b[39;00m)] \u001b[38;5;241m*\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mndim\n\u001b[1;32m   1308\u001b[0m     indexer[axis] \u001b[38;5;241m=\u001b[39m locs\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/core/indexes/multi.py:3422\u001b[0m, in \u001b[0;36mMultiIndex.get_locs\u001b[0;34m(self, seq)\u001b[0m\n\u001b[1;32m   3418\u001b[0m     \u001b[38;5;28;01mcontinue\u001b[39;00m\n\u001b[1;32m   3420\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   3421\u001b[0m     \u001b[38;5;66;03m# a slice or a single label\u001b[39;00m\n\u001b[0;32m-> 3422\u001b[0m     lvl_indexer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_level_indexer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mi\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindexer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mindexer\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   3424\u001b[0m \u001b[38;5;66;03m# update indexer\u001b[39;00m\n\u001b[1;32m   3425\u001b[0m lvl_indexer \u001b[38;5;241m=\u001b[39m _to_bool_indexer(lvl_indexer)\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/core/indexes/multi.py:3262\u001b[0m, in \u001b[0;36mMultiIndex._get_level_indexer\u001b[0;34m(self, key, level, indexer)\u001b[0m\n\u001b[1;32m   3258\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mslice\u001b[39m(i, j, step)\n\u001b[1;32m   3260\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 3262\u001b[0m     idx \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_loc_single_level_index\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlevel_index\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   3264\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m level \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lexsort_depth \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m   3265\u001b[0m         \u001b[38;5;66;03m# Desired level is not sorted\u001b[39;00m\n\u001b[1;32m   3266\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(idx, \u001b[38;5;28mslice\u001b[39m):\n\u001b[1;32m   3267\u001b[0m             \u001b[38;5;66;03m# test_get_loc_partial_timestamp_multiindex\u001b[39;00m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/core/indexes/multi.py:2848\u001b[0m, in \u001b[0;36mMultiIndex._get_loc_single_level_index\u001b[0;34m(self, level_index, key)\u001b[0m\n\u001b[1;32m   2846\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m\n\u001b[1;32m   2847\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 2848\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mlevel_index\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/opt/anaconda3/envs/cryptodatapy/lib/python3.9/site-packages/pandas/core/indexes/base.py:3802\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   3800\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine\u001b[38;5;241m.\u001b[39mget_loc(casted_key)\n\u001b[1;32m   3801\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[0;32m-> 3802\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01merr\u001b[39;00m\n\u001b[1;32m   3803\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m:\n\u001b[1;32m   3804\u001b[0m     \u001b[38;5;66;03m# If we have a listlike key, _check_indexing_error will raise\u001b[39;00m\n\u001b[1;32m   3805\u001b[0m     \u001b[38;5;66;03m#  InvalidIndexError. Otherwise we fall through and re-raise\u001b[39;00m\n\u001b[1;32m   3806\u001b[0m     \u001b[38;5;66;03m#  the TypeError.\u001b[39;00m\n\u001b[1;32m   3807\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_check_indexing_error(key)\n",
-      "\u001b[0;31mKeyError\u001b[0m: 'OCEAN'"
-     ]
+     "data": {
+      "text/plain": [
+       "['CVC',\n",
+       " 'CTK',\n",
+       " 'STRAX',\n",
+       " 'STPT',\n",
+       " 'DGB',\n",
+       " 'CVX',\n",
+       " 'FTT',\n",
+       " 'GLMR',\n",
+       " 'OCEAN',\n",
+       " 'SLP',\n",
+       " 'AGIX',\n",
+       " 'RAY',\n",
+       " 'MDT',\n",
+       " 'SC',\n",
+       " 'SNT',\n",
+       " 'IDEX',\n",
+       " 'RAD',\n",
+       " 'WAVES']"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "clean_df.loc[:, 'OCEAN', :]"
+    "clean.filtered_tickers"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
-   "id": "ad5a885c",
+   "execution_count": 38,
+   "id": "e4693e52",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<cryptodatapy.transform.clean.CleanData at 0x7fb888103af0>"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean.filter_outliers(od_method='mad', excl_cols=['volume', 'funding_rate'], thresh_val=10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "311ee6ed",
    "metadata": {},
    "outputs": [
     {
@@ -787,71 +1215,259 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
+       "      <th></th>\n",
        "      <th>open</th>\n",
        "      <th>high</th>\n",
        "      <th>low</th>\n",
        "      <th>close</th>\n",
-       "      <th>volume</th>\n",
-       "      <th>funding_rate</th>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>date</th>\n",
+       "      <th>ticker</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2010-07-17</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-07-18</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-07-19</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-07-20</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-07-21</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th rowspan=\"5\" valign=\"top\">2024-08-04</th>\n",
+       "      <th>ZEN</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>9.112</td>\n",
+       "      <td>8.285</td>\n",
+       "      <td>8.462</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZIL</th>\n",
+       "      <td>0.01422</td>\n",
+       "      <td>0.01441</td>\n",
+       "      <td>0.01392</td>\n",
+       "      <td>0.01396</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZK</th>\n",
+       "      <td>0.11451</td>\n",
+       "      <td>0.11673</td>\n",
+       "      <td>0.10857</td>\n",
+       "      <td>0.10874</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZRO</th>\n",
+       "      <td>3.631</td>\n",
+       "      <td>3.648</td>\n",
+       "      <td>3.362</td>\n",
+       "      <td>3.367</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZRX</th>\n",
+       "      <td>0.3055</td>\n",
+       "      <td>0.3121</td>\n",
+       "      <td>0.2983</td>\n",
+       "      <td>0.2988</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>357696 rows × 4 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      open     high      low    close\n",
+       "date       ticker                                    \n",
+       "2010-07-17 BTC        <NA>     <NA>     <NA>     <NA>\n",
+       "2010-07-18 BTC        <NA>     <NA>     <NA>     <NA>\n",
+       "2010-07-19 BTC        <NA>     <NA>     <NA>     <NA>\n",
+       "2010-07-20 BTC        <NA>     <NA>     <NA>     <NA>\n",
+       "2010-07-21 BTC        <NA>     <NA>     <NA>     <NA>\n",
+       "...                    ...      ...      ...      ...\n",
+       "2024-08-04 ZEN        <NA>    9.112    8.285    8.462\n",
+       "           ZIL     0.01422  0.01441  0.01392  0.01396\n",
+       "           ZK      0.11451  0.11673  0.10857  0.10874\n",
+       "           ZRO       3.631    3.648    3.362    3.367\n",
+       "           ZRX      0.3055   0.3121   0.2983   0.2988\n",
+       "\n",
+       "[357696 rows x 4 columns]"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean.df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "83caa2c6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<cryptodatapy.transform.clean.CleanData at 0x7fb888103af0>"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean.repair_outliers(imp_method='fcst')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "f4c21352",
+   "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></th>\n",
+       "      <th>open</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>close</th>\n",
+       "      <th>volume</th>\n",
+       "      <th>funding_rate</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>date</th>\n",
+       "      <th>ticker</th>\n",
+       "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
        "      <th></th>\n",
-       "      <th></th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>2015-06-12</th>\n",
-       "      <td>229.88</td>\n",
-       "      <td>231.58</td>\n",
-       "      <td>229.29</td>\n",
-       "      <td>230.46</td>\n",
-       "      <td>40744.820</td>\n",
+       "      <th>2010-07-17</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>42.99</td>\n",
+       "      <td>43.76</td>\n",
+       "      <td>40.99</td>\n",
+       "      <td>41.01</td>\n",
+       "      <td>2.000000e+01</td>\n",
        "      <td>0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2015-06-13</th>\n",
-       "      <td>230.46</td>\n",
-       "      <td>233.14</td>\n",
-       "      <td>229.01</td>\n",
-       "      <td>232.48</td>\n",
-       "      <td>38008.730</td>\n",
+       "      <th>2010-07-18</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>0.07921</td>\n",
+       "      <td>0.08181</td>\n",
+       "      <td>0.06634</td>\n",
+       "      <td>0.07921</td>\n",
+       "      <td>7.501000e+01</td>\n",
        "      <td>0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2015-06-14</th>\n",
-       "      <td>232.48</td>\n",
-       "      <td>235.51</td>\n",
-       "      <td>232.09</td>\n",
-       "      <td>233.75</td>\n",
-       "      <td>32894.870</td>\n",
+       "      <th>2010-07-19</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>0.07474</td>\n",
+       "      <td>0.07921</td>\n",
+       "      <td>0.0505</td>\n",
+       "      <td>0.06262</td>\n",
+       "      <td>5.740000e+02</td>\n",
        "      <td>0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2015-06-15</th>\n",
-       "      <td>233.75</td>\n",
-       "      <td>238.55</td>\n",
-       "      <td>233.29</td>\n",
-       "      <td>237.0</td>\n",
-       "      <td>63467.090</td>\n",
+       "      <th>2010-07-20</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>0.06868</td>\n",
+       "      <td>0.07344</td>\n",
+       "      <td>0.0505</td>\n",
+       "      <td>0.06052</td>\n",
+       "      <td>2.620000e+02</td>\n",
        "      <td>0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2015-06-16</th>\n",
-       "      <td>237.0</td>\n",
-       "      <td>254.15</td>\n",
-       "      <td>235.7</td>\n",
-       "      <td>249.82</td>\n",
-       "      <td>122473.610</td>\n",
+       "      <th>2010-07-21</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>0.06262</td>\n",
+       "      <td>0.06767</td>\n",
+       "      <td>0.0505</td>\n",
+       "      <td>0.05842</td>\n",
+       "      <td>5.750000e+02</td>\n",
        "      <td>0.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
+       "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
@@ -860,128 +1476,691 @@
        "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2024-07-31</th>\n",
-       "      <td>66159.3</td>\n",
-       "      <td>66826.3</td>\n",
-       "      <td>64500.4</td>\n",
-       "      <td>64601.8</td>\n",
-       "      <td>246389.446</td>\n",
-       "      <td>0.000141</td>\n",
+       "      <th rowspan=\"5\" valign=\"top\">2024-08-04</th>\n",
+       "      <th>ZEN</th>\n",
+       "      <td>9.657</td>\n",
+       "      <td>9.112</td>\n",
+       "      <td>8.285</td>\n",
+       "      <td>8.462</td>\n",
+       "      <td>2.071124e+06</td>\n",
+       "      <td>0.000194</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2024-08-01</th>\n",
-       "      <td>64601.8</td>\n",
-       "      <td>65650.0</td>\n",
-       "      <td>62271.2</td>\n",
-       "      <td>65328.9</td>\n",
-       "      <td>372654.590</td>\n",
-       "      <td>0.000282</td>\n",
+       "      <th>ZIL</th>\n",
+       "      <td>0.01422</td>\n",
+       "      <td>0.01441</td>\n",
+       "      <td>0.01392</td>\n",
+       "      <td>0.01396</td>\n",
+       "      <td>2.048626e+08</td>\n",
+       "      <td>-0.000031</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2024-08-02</th>\n",
-       "      <td>65329.0</td>\n",
-       "      <td>65577.0</td>\n",
-       "      <td>61200.2</td>\n",
-       "      <td>61483.7</td>\n",
-       "      <td>421628.420</td>\n",
-       "      <td>0.000300</td>\n",
+       "      <th>ZK</th>\n",
+       "      <td>0.11451</td>\n",
+       "      <td>0.11673</td>\n",
+       "      <td>0.10857</td>\n",
+       "      <td>0.10874</td>\n",
+       "      <td>3.833253e+08</td>\n",
+       "      <td>0.000200</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2024-08-03</th>\n",
-       "      <td>61483.7</td>\n",
-       "      <td>63871.5</td>\n",
-       "      <td>59800.0</td>\n",
-       "      <td>60684.6</td>\n",
-       "      <td>290469.956</td>\n",
-       "      <td>0.000240</td>\n",
+       "      <th>ZRO</th>\n",
+       "      <td>3.631</td>\n",
+       "      <td>3.648</td>\n",
+       "      <td>3.362</td>\n",
+       "      <td>3.367</td>\n",
+       "      <td>7.049472e+07</td>\n",
+       "      <td>0.000184</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2024-08-04</th>\n",
-       "      <td>60684.5</td>\n",
-       "      <td>61089.5</td>\n",
-       "      <td>60080.5</td>\n",
-       "      <td>60357.6</td>\n",
-       "      <td>85220.266</td>\n",
-       "      <td>0.000153</td>\n",
+       "      <th>ZRX</th>\n",
+       "      <td>0.3055</td>\n",
+       "      <td>0.3121</td>\n",
+       "      <td>0.2983</td>\n",
+       "      <td>0.2988</td>\n",
+       "      <td>9.810764e+06</td>\n",
+       "      <td>0.000186</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>3342 rows × 6 columns</p>\n",
+       "<p>357696 rows × 6 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "               open     high      low    close      volume  funding_rate\n",
-       "date                                                                    \n",
-       "2015-06-12   229.88   231.58   229.29   230.46   40744.820      0.000000\n",
-       "2015-06-13   230.46   233.14   229.01   232.48   38008.730      0.000000\n",
-       "2015-06-14   232.48   235.51   232.09   233.75   32894.870      0.000000\n",
-       "2015-06-15   233.75   238.55   233.29    237.0   63467.090      0.000000\n",
-       "2015-06-16    237.0   254.15    235.7   249.82  122473.610      0.000000\n",
-       "...             ...      ...      ...      ...         ...           ...\n",
-       "2024-07-31  66159.3  66826.3  64500.4  64601.8  246389.446      0.000141\n",
-       "2024-08-01  64601.8  65650.0  62271.2  65328.9  372654.590      0.000282\n",
-       "2024-08-02  65329.0  65577.0  61200.2  61483.7  421628.420      0.000300\n",
-       "2024-08-03  61483.7  63871.5  59800.0  60684.6  290469.956      0.000240\n",
-       "2024-08-04  60684.5  61089.5  60080.5  60357.6   85220.266      0.000153\n",
+       "                      open     high      low    close        volume  \\\n",
+       "date       ticker                                                     \n",
+       "2010-07-17 BTC       42.99    43.76    40.99    41.01  2.000000e+01   \n",
+       "2010-07-18 BTC     0.07921  0.08181  0.06634  0.07921  7.501000e+01   \n",
+       "2010-07-19 BTC     0.07474  0.07921   0.0505  0.06262  5.740000e+02   \n",
+       "2010-07-20 BTC     0.06868  0.07344   0.0505  0.06052  2.620000e+02   \n",
+       "2010-07-21 BTC     0.06262  0.06767   0.0505  0.05842  5.750000e+02   \n",
+       "...                    ...      ...      ...      ...           ...   \n",
+       "2024-08-04 ZEN       9.657    9.112    8.285    8.462  2.071124e+06   \n",
+       "           ZIL     0.01422  0.01441  0.01392  0.01396  2.048626e+08   \n",
+       "           ZK      0.11451  0.11673  0.10857  0.10874  3.833253e+08   \n",
+       "           ZRO       3.631    3.648    3.362    3.367  7.049472e+07   \n",
+       "           ZRX      0.3055   0.3121   0.2983   0.2988  9.810764e+06   \n",
+       "\n",
+       "                   funding_rate  \n",
+       "date       ticker                \n",
+       "2010-07-17 BTC         0.000000  \n",
+       "2010-07-18 BTC         0.000000  \n",
+       "2010-07-19 BTC         0.000000  \n",
+       "2010-07-20 BTC         0.000000  \n",
+       "2010-07-21 BTC         0.000000  \n",
+       "...                         ...  \n",
+       "2024-08-04 ZEN         0.000194  \n",
+       "           ZIL        -0.000031  \n",
+       "           ZK          0.000200  \n",
+       "           ZRO         0.000184  \n",
+       "           ZRX         0.000186  \n",
        "\n",
-       "[3342 rows x 6 columns]"
+       "[357696 rows x 6 columns]"
       ]
      },
-     "execution_count": 28,
+     "execution_count": 41,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "clean_df.loc[:, 'BTC', :]"
+    "clean.df"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
-   "id": "a9c262fc",
+   "execution_count": 42,
+   "id": "66b3d8d2",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<cryptodatapy.transform.clean.CleanData at 0x7fb888103af0>"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "clean_df.to_parquet('s3://factorlab-data/binance_historical_ohlcv_daily.parquet')"
+    "clean.filter_avg_trading_val(thresh_val=1000000)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
-   "id": "893e3e38",
+   "execution_count": 43,
+   "id": "b7f23056",
+   "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></th>\n",
+       "      <th>open</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>close</th>\n",
+       "      <th>volume</th>\n",
+       "      <th>funding_rate</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>date</th>\n",
+       "      <th>ticker</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2010-07-17</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-07-18</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-07-19</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-07-20</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-07-21</th>\n",
+       "      <th>BTC</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th rowspan=\"5\" valign=\"top\">2024-08-04</th>\n",
+       "      <th>ZEN</th>\n",
+       "      <td>9.657</td>\n",
+       "      <td>9.112</td>\n",
+       "      <td>8.285</td>\n",
+       "      <td>8.462</td>\n",
+       "      <td>2071124.0</td>\n",
+       "      <td>0.000194</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZIL</th>\n",
+       "      <td>0.01422</td>\n",
+       "      <td>0.01441</td>\n",
+       "      <td>0.01392</td>\n",
+       "      <td>0.01396</td>\n",
+       "      <td>204862627.0</td>\n",
+       "      <td>-0.000031</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZK</th>\n",
+       "      <td>0.11451</td>\n",
+       "      <td>0.11673</td>\n",
+       "      <td>0.10857</td>\n",
+       "      <td>0.10874</td>\n",
+       "      <td>383325323.0</td>\n",
+       "      <td>0.000200</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZRO</th>\n",
+       "      <td>3.631</td>\n",
+       "      <td>3.648</td>\n",
+       "      <td>3.362</td>\n",
+       "      <td>3.367</td>\n",
+       "      <td>70494717.0</td>\n",
+       "      <td>0.000184</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZRX</th>\n",
+       "      <td>0.3055</td>\n",
+       "      <td>0.3121</td>\n",
+       "      <td>0.2983</td>\n",
+       "      <td>0.2988</td>\n",
+       "      <td>9810764.1</td>\n",
+       "      <td>0.000186</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>357696 rows × 6 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      open     high      low    close       volume  \\\n",
+       "date       ticker                                                    \n",
+       "2010-07-17 BTC        <NA>     <NA>     <NA>     <NA>          NaN   \n",
+       "2010-07-18 BTC        <NA>     <NA>     <NA>     <NA>          NaN   \n",
+       "2010-07-19 BTC        <NA>     <NA>     <NA>     <NA>          NaN   \n",
+       "2010-07-20 BTC        <NA>     <NA>     <NA>     <NA>          NaN   \n",
+       "2010-07-21 BTC        <NA>     <NA>     <NA>     <NA>          NaN   \n",
+       "...                    ...      ...      ...      ...          ...   \n",
+       "2024-08-04 ZEN       9.657    9.112    8.285    8.462    2071124.0   \n",
+       "           ZIL     0.01422  0.01441  0.01392  0.01396  204862627.0   \n",
+       "           ZK      0.11451  0.11673  0.10857  0.10874  383325323.0   \n",
+       "           ZRO       3.631    3.648    3.362    3.367   70494717.0   \n",
+       "           ZRX      0.3055   0.3121   0.2983   0.2988    9810764.1   \n",
+       "\n",
+       "                   funding_rate  \n",
+       "date       ticker                \n",
+       "2010-07-17 BTC              NaN  \n",
+       "2010-07-18 BTC              NaN  \n",
+       "2010-07-19 BTC              NaN  \n",
+       "2010-07-20 BTC              NaN  \n",
+       "2010-07-21 BTC              NaN  \n",
+       "...                         ...  \n",
+       "2024-08-04 ZEN         0.000194  \n",
+       "           ZIL        -0.000031  \n",
+       "           ZK          0.000200  \n",
+       "           ZRO         0.000184  \n",
+       "           ZRX         0.000186  \n",
+       "\n",
+       "[357696 rows x 6 columns]"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean.df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "id": "b5ac345d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['CVC',\n",
+       " 'CTK',\n",
+       " 'STRAX',\n",
+       " 'STPT',\n",
+       " 'DGB',\n",
+       " 'CVX',\n",
+       " 'FTT',\n",
+       " 'GLMR',\n",
+       " 'OCEAN',\n",
+       " 'SLP',\n",
+       " 'AGIX',\n",
+       " 'RAY',\n",
+       " 'MDT',\n",
+       " 'SC',\n",
+       " 'SNT',\n",
+       " 'IDEX',\n",
+       " 'RAD',\n",
+       " 'WAVES']"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean.filtered_tickers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "id": "6d36d4ce",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<cryptodatapy.transform.clean.CleanData at 0x7fb888103af0>"
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean.filter_missing_vals_gaps()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "7fe432d5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['CVC',\n",
+       " 'CTK',\n",
+       " 'STRAX',\n",
+       " 'STPT',\n",
+       " 'DGB',\n",
+       " 'CVX',\n",
+       " 'FTT',\n",
+       " 'GLMR',\n",
+       " 'OCEAN',\n",
+       " 'SLP',\n",
+       " 'AGIX',\n",
+       " 'RAY',\n",
+       " 'MDT',\n",
+       " 'SC',\n",
+       " 'SNT',\n",
+       " 'IDEX',\n",
+       " 'RAD',\n",
+       " 'WAVES']"
+      ]
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean.filtered_tickers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "f7cbdbae",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<cryptodatapy.transform.clean.CleanData at 0x7fb888103af0>"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean.filter_min_nobs(ts_obs=1400, cs_obs=5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "f13d9f1f",
+   "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></th>\n",
+       "      <th>open</th>\n",
+       "      <th>high</th>\n",
+       "      <th>low</th>\n",
+       "      <th>close</th>\n",
+       "      <th>volume</th>\n",
+       "      <th>funding_rate</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>date</th>\n",
+       "      <th>ticker</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th rowspan=\"5\" valign=\"top\">2017-06-18</th>\n",
+       "      <th>BAT</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>BTC</th>\n",
+       "      <td>2655.1</td>\n",
+       "      <td>2676.04</td>\n",
+       "      <td>2488.59</td>\n",
+       "      <td>2539.56</td>\n",
+       "      <td>9.200422e+04</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DASH</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DOGE</th>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>&lt;NA&gt;</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ETC</th>\n",
+       "      <td>21.98</td>\n",
+       "      <td>23.8</td>\n",
+       "      <td>19.5</td>\n",
+       "      <td>20.27</td>\n",
+       "      <td>1.306320e+06</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th rowspan=\"5\" valign=\"top\">2024-08-04</th>\n",
+       "      <th>XTZ</th>\n",
+       "      <td>0.685</td>\n",
+       "      <td>0.693</td>\n",
+       "      <td>0.677</td>\n",
+       "      <td>0.679</td>\n",
+       "      <td>5.373374e+06</td>\n",
+       "      <td>0.000200</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>YFI</th>\n",
+       "      <td>5341.0</td>\n",
+       "      <td>5341.0</td>\n",
+       "      <td>5196.0</td>\n",
+       "      <td>5198.0</td>\n",
+       "      <td>4.281050e+02</td>\n",
+       "      <td>0.000169</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZEC</th>\n",
+       "      <td>31.76</td>\n",
+       "      <td>34.44</td>\n",
+       "      <td>31.28</td>\n",
+       "      <td>31.55</td>\n",
+       "      <td>1.348085e+06</td>\n",
+       "      <td>0.000191</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZIL</th>\n",
+       "      <td>0.01422</td>\n",
+       "      <td>0.01441</td>\n",
+       "      <td>0.01392</td>\n",
+       "      <td>0.01396</td>\n",
+       "      <td>2.048626e+08</td>\n",
+       "      <td>-0.000031</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ZRX</th>\n",
+       "      <td>0.3055</td>\n",
+       "      <td>0.3121</td>\n",
+       "      <td>0.2983</td>\n",
+       "      <td>0.2988</td>\n",
+       "      <td>9.810764e+06</td>\n",
+       "      <td>0.000186</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>136630 rows × 6 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      open     high      low    close        volume  \\\n",
+       "date       ticker                                                     \n",
+       "2017-06-18 BAT        <NA>     <NA>     <NA>     <NA>           NaN   \n",
+       "           BTC      2655.1  2676.04  2488.59  2539.56  9.200422e+04   \n",
+       "           DASH       <NA>     <NA>     <NA>     <NA>           NaN   \n",
+       "           DOGE       <NA>     <NA>     <NA>     <NA>           NaN   \n",
+       "           ETC       21.98     23.8     19.5    20.27  1.306320e+06   \n",
+       "...                    ...      ...      ...      ...           ...   \n",
+       "2024-08-04 XTZ       0.685    0.693    0.677    0.679  5.373374e+06   \n",
+       "           YFI      5341.0   5341.0   5196.0   5198.0  4.281050e+02   \n",
+       "           ZEC       31.76    34.44    31.28    31.55  1.348085e+06   \n",
+       "           ZIL     0.01422  0.01441  0.01392  0.01396  2.048626e+08   \n",
+       "           ZRX      0.3055   0.3121   0.2983   0.2988  9.810764e+06   \n",
+       "\n",
+       "                   funding_rate  \n",
+       "date       ticker                \n",
+       "2017-06-18 BAT              NaN  \n",
+       "           BTC         0.000000  \n",
+       "           DASH             NaN  \n",
+       "           DOGE             NaN  \n",
+       "           ETC         0.000000  \n",
+       "...                         ...  \n",
+       "2024-08-04 XTZ         0.000200  \n",
+       "           YFI         0.000169  \n",
+       "           ZEC         0.000191  \n",
+       "           ZIL        -0.000031  \n",
+       "           ZRX         0.000186  \n",
+       "\n",
+       "[136630 rows x 6 columns]"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean.df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "a9b1764c",
    "metadata": {},
    "outputs": [],
    "source": [
-    "clean_df.to_parquet('../../../../factorlab/notebooks/binance_historical_ohlcv_daily.parquet')"
+    "# # clean data\n",
+    "# clean_df = clean.filter_delisted_tickers().\\\n",
+    "#                          filter_outliers(od_method='mad', excl_cols=['volume', 'funding_rate'], thresh_val=10).\\\n",
+    "#                          repair_outliers(imp_method='fcst').\\\n",
+    "#                          filter_avg_trading_val(thresh_val=1000000).\\\n",
+    "#                          filter_missing_vals_gaps().\\\n",
+    "#                          filter_min_nobs(ts_obs=1500, cs_obs=10).\\\n",
+    "#                          get(attr='df').dropna(how='all')"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8a962fa7",
+   "id": "572d7a2e",
    "metadata": {},
    "outputs": [],
    "source": []
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
-   "id": "54b818cd",
+   "execution_count": 53,
+   "id": "99857595",
    "metadata": {},
    "outputs": [],
    "source": [
-    "clean_df.to_csv('../../../../factorlab/notebooks/binance_historical_ohlcv_daily.csv')"
+    "df.to_parquet('s3://factorlab-data/binance_historical_ohlcv_daily.parquet')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
-   "id": "a1c49f01",
+   "execution_count": 54,
+   "id": "15e66225",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "clean.df.dropna(how='all').to_parquet('../../../../factorlab/notebooks/binance_historical_ohlcv_daily.parquet')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8a962fa7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "54b818cd",
    "metadata": {},
    "outputs": [],
    "source": [
-    "clean_df.to_csv('s3://factorlab-data/binance_historical_ohlcv_daily.csv')"
+    "clean.df.dropna(how='all').to_csv('../../../../factorlab/notebooks/binance_historical_ohlcv_daily.csv')"
    ]
   },
   {
@@ -995,7 +2174,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f9488eba",
+   "id": "da953cbf",
    "metadata": {},
    "outputs": [],
    "source": []

cryptodatapy 0.2.4__py3-none-any.whl → 0.2.5__py3-none-any.whl

cryptodatapy 0.2.4py3-none-any.whl → 0.2.5py3-none-any.whl