Fixing file system issue caused by Communit Edition disablement of FU…

…SE mount
Amrit-Hub · Dec 3, 2020 · e1e072b · e1e072b
1 parent 74c389c
commit e1e072b
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/2020-04-15 | Data Analysis with Pandas /Data-Analysis-with-Pandas.ipynb b/2020-04-15 | Data Analysis with Pandas /Data-Analysis-with-Pandas.ipynb
diff --git a/2020-04-15 | Data Analysis with Pandas /Plotting My Area Lab.ipynb b/2020-04-15 | Data Analysis with Pandas /Plotting My Area Lab.ipynb
@@ -1 +1 @@
-{"cells":[{"cell_type":"markdown","source":["## Plotting My Area\n\nUse the starter code below to explore the data for your area"],"metadata":{}},{"cell_type":"code","source":["import datetime\nimport glob\nimport pandas as pd\n\npath = \"/dbfs/databricks-datasets/COVID/CSSEGISandData/csse_covid_19_data/csse_covid_19_daily_reports\"\nall_files = glob.glob(path + \"/*.csv\")\n\ndfs = []\n\nfor filename in all_files:\n  temp_df = pd.read_csv(filename)\n  temp_df.columns = [c.replace(\"/\", \"_\") for c in temp_df.columns]\n  temp_df.columns = [c.replace(\" \", \"_\") for c in temp_df.columns]\n  \n  month, day, year = filename.split(\"/\")[-1].replace(\".csv\", \"\").split(\"-\")\n  d = datetime.date(int(year), int(month), int(day))\n  temp_df[\"Date\"] = d\n\n  dfs.append(temp_df)\n  \nall_days_df = pd.concat(dfs, axis=0, ignore_index=True, sort=False)\nall_days_df = all_days_df.drop([\"Latitude\", \"Longitude\", \"Lat\", \"Long_\", \"FIPS\", \"Combined_Key\", \"Last_Update\"], axis=1)\n\nall_days_df.head(10)"],"metadata":{},"outputs":[{"metadata":{},"output_type":"display_data","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>Province_State</th>\n      <th>Country_Region</th>\n      <th>Confirmed</th>\n      <th>Deaths</th>\n      <th>Recovered</th>\n      <th>Date</th>\n      <th>Admin2</th>\n      <th>Active</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Anhui</td>\n      <td>Mainland China</td>\n      <td>1.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2020-01-22</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Beijing</td>\n      <td>Mainland China</td>\n      <td>14.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2020-01-22</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Chongqing</td>\n      <td>Mainland China</td>\n      <td>6.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2020-01-22</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Fujian</td>\n      <td>Mainland China</td>\n      <td>1.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2020-01-22</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Gansu</td>\n      <td>Mainland China</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2020-01-22</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Guangdong</td>\n      <td>Mainland China</td>\n      <td>26.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2020-01-22</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Guangxi</td>\n      <td>Mainland China</td>\n      <td>2.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2020-01-22</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>Guizhou</td>\n      <td>Mainland China</td>\n      <td>1.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2020-01-22</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Hainan</td>\n      <td>Mainland China</td>\n      <td>4.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2020-01-22</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Hebei</td>\n      <td>Mainland China</td>\n      <td>1.0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2020-01-22</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n</div>"]}}],"execution_count":2},{"cell_type":"code","source":[""],"metadata":{},"outputs":[],"execution_count":3}],"metadata":{"name":"Plotting My Area Lab","notebookId":17365945},"nbformat":4,"nbformat_minor":0}
+{"cells":[{"cell_type":"markdown","source":["## Plotting My Area\n\nUse the starter code below to explore the data for your area"],"metadata":{"application/vnd.databricks.v1+cell":{"title":"","showTitle":false,"inputWidgets":{},"nuid":"6ac80b32-96fe-419b-8de0-78435d8152e4"}}},{"cell_type":"code","source":["src_path_base = \"dbfs:/databricks-datasets/COVID/CSSEGISandData/csse_covid_19_data/csse_covid_19_daily_reports/\"\ndest_path_base = \"file:////tmp/covid_daily_reports/\"\n\nfiles = [\n '11-21-2020.csv',\n '11-22-2020.csv',\n '11-23-2020.csv',\n '11-24-2020.csv',\n '11-25-2020.csv',\n '11-26-2020.csv',\n '11-27-2020.csv',\n '11-28-2020.csv',\n '11-29-2020.csv',\n '11-30-2020.csv'\n]\n\nall_files = []\n\nfor file in files:\n  filename = dest_path_base+file\n  dbutils.fs.cp(src_path_base+file, filename)\n  all_files.append(filename)\n\nall_files"],"metadata":{"application/vnd.databricks.v1+cell":{"title":"","showTitle":false,"inputWidgets":{},"nuid":"7698baa0-81eb-476b-811c-8367680430eb"}},"outputs":[{"output_type":"display_data","metadata":{"application/vnd.databricks.v1+output":{"datasetInfos":[],"data":"<div class=\"ansiout\">Out[3]: [&#39;file:////tmp/covid_daily_reports/11-21-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-22-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-23-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-24-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-25-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-26-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-27-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-28-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-29-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-30-2020.csv&#39;]</div>","removedWidgets":[],"addedWidgets":{},"type":"html","arguments":{}}},"output_type":"display_data","data":{"text/html":["<style scoped>\n  .ansiout {\n    display: block;\n    unicode-bidi: embed;\n    white-space: pre-wrap;\n    word-wrap: break-word;\n    word-break: break-all;\n    font-family: \"Source Code Pro\", \"Menlo\", monospace;;\n    font-size: 13px;\n    color: #555;\n    margin-left: 4px;\n    line-height: 19px;\n  }\n</style>\n<div class=\"ansiout\">Out[3]: [&#39;file:////tmp/covid_daily_reports/11-21-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-22-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-23-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-24-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-25-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-26-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-27-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-28-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-29-2020.csv&#39;,\n &#39;file:////tmp/covid_daily_reports/11-30-2020.csv&#39;]</div>"]}}],"execution_count":0},{"cell_type":"code","source":["import datetime\nimport pandas as pd\n\ndfs = []\n\nfor filename in all_files:\n  temp_df = pd.read_csv(filename)\n  temp_df.columns = [c.replace(\"/\", \"_\") for c in temp_df.columns]\n  temp_df.columns = [c.replace(\" \", \"_\") for c in temp_df.columns]\n  \n  month, day, year = filename.split(\"/\")[-1].replace(\".csv\", \"\").split(\"-\")\n  d = datetime.date(int(year), int(month), int(day))\n  temp_df[\"Date\"] = d\n\n  dfs.append(temp_df)\n  \nall_days_df = pd.concat(dfs, axis=0, ignore_index=True, sort=False)\nall_days_df = all_days_df.drop([\"Lat\", \"Long_\", \"FIPS\", \"Combined_Key\", \"Last_Update\"], axis=1)\n\nall_days_df.head(10)"],"metadata":{"application/vnd.databricks.v1+cell":{"title":"","showTitle":false,"inputWidgets":{},"nuid":"0c71a076-4e9e-434c-97b4-75bc5fceff57"}},"outputs":[{"output_type":"display_data","metadata":{"application/vnd.databricks.v1+output":{"datasetInfos":[],"data":"<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>Admin2</th>\n      <th>Province_State</th>\n      <th>Country_Region</th>\n      <th>Confirmed</th>\n      <th>Deaths</th>\n      <th>Recovered</th>\n      <th>Active</th>\n      <th>Incident_Rate</th>\n      <th>Case_Fatality_Ratio</th>\n      <th>Date</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Afghanistan</td>\n      <td>44503</td>\n      <td>1675</td>\n      <td>35422</td>\n      <td>7406.0</td>\n      <td>114.320310</td>\n      <td>3.763791</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Albania</td>\n      <td>32196</td>\n      <td>685</td>\n      <td>15469</td>\n      <td>16042.0</td>\n      <td>1118.771284</td>\n      <td>2.127593</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Algeria</td>\n      <td>73774</td>\n      <td>2255</td>\n      <td>48183</td>\n      <td>23336.0</td>\n      <td>168.237732</td>\n      <td>3.056632</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Andorra</td>\n      <td>6207</td>\n      <td>76</td>\n      <td>5290</td>\n      <td>841.0</td>\n      <td>8033.391574</td>\n      <td>1.224424</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Angola</td>\n      <td>14413</td>\n      <td>336</td>\n      <td>7273</td>\n      <td>6804.0</td>\n      <td>43.853473</td>\n      <td>2.331229</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Antigua and Barbuda</td>\n      <td>139</td>\n      <td>4</td>\n      <td>128</td>\n      <td>7.0</td>\n      <td>141.941018</td>\n      <td>2.877698</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Argentina</td>\n      <td>1366182</td>\n      <td>36902</td>\n      <td>1187053</td>\n      <td>142227.0</td>\n      <td>3022.808967</td>\n      <td>2.701104</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Armenia</td>\n      <td>124839</td>\n      <td>1931</td>\n      <td>92829</td>\n      <td>30079.0</td>\n      <td>4212.930872</td>\n      <td>1.546792</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>NaN</td>\n      <td>Australian Capital Territory</td>\n      <td>Australia</td>\n      <td>115</td>\n      <td>3</td>\n      <td>111</td>\n      <td>1.0</td>\n      <td>26.862883</td>\n      <td>2.608696</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>NaN</td>\n      <td>New South Wales</td>\n      <td>Australia</td>\n      <td>4538</td>\n      <td>53</td>\n      <td>3173</td>\n      <td>1312.0</td>\n      <td>55.900468</td>\n      <td>1.167915</td>\n      <td>2020-11-21</td>\n    </tr>\n  </tbody>\n</table>\n</div>","textData":"<div class=\"ansiout\">Out[5]: </div>","removedWidgets":[],"addedWidgets":{},"type":"htmlSandbox","arguments":{}}},"output_type":"display_data","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>Admin2</th>\n      <th>Province_State</th>\n      <th>Country_Region</th>\n      <th>Confirmed</th>\n      <th>Deaths</th>\n      <th>Recovered</th>\n      <th>Active</th>\n      <th>Incident_Rate</th>\n      <th>Case_Fatality_Ratio</th>\n      <th>Date</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Afghanistan</td>\n      <td>44503</td>\n      <td>1675</td>\n      <td>35422</td>\n      <td>7406.0</td>\n      <td>114.320310</td>\n      <td>3.763791</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Albania</td>\n      <td>32196</td>\n      <td>685</td>\n      <td>15469</td>\n      <td>16042.0</td>\n      <td>1118.771284</td>\n      <td>2.127593</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Algeria</td>\n      <td>73774</td>\n      <td>2255</td>\n      <td>48183</td>\n      <td>23336.0</td>\n      <td>168.237732</td>\n      <td>3.056632</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Andorra</td>\n      <td>6207</td>\n      <td>76</td>\n      <td>5290</td>\n      <td>841.0</td>\n      <td>8033.391574</td>\n      <td>1.224424</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Angola</td>\n      <td>14413</td>\n      <td>336</td>\n      <td>7273</td>\n      <td>6804.0</td>\n      <td>43.853473</td>\n      <td>2.331229</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Antigua and Barbuda</td>\n      <td>139</td>\n      <td>4</td>\n      <td>128</td>\n      <td>7.0</td>\n      <td>141.941018</td>\n      <td>2.877698</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Argentina</td>\n      <td>1366182</td>\n      <td>36902</td>\n      <td>1187053</td>\n      <td>142227.0</td>\n      <td>3022.808967</td>\n      <td>2.701104</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Armenia</td>\n      <td>124839</td>\n      <td>1931</td>\n      <td>92829</td>\n      <td>30079.0</td>\n      <td>4212.930872</td>\n      <td>1.546792</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>NaN</td>\n      <td>Australian Capital Territory</td>\n      <td>Australia</td>\n      <td>115</td>\n      <td>3</td>\n      <td>111</td>\n      <td>1.0</td>\n      <td>26.862883</td>\n      <td>2.608696</td>\n      <td>2020-11-21</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>NaN</td>\n      <td>New South Wales</td>\n      <td>Australia</td>\n      <td>4538</td>\n      <td>53</td>\n      <td>3173</td>\n      <td>1312.0</td>\n      <td>55.900468</td>\n      <td>1.167915</td>\n      <td>2020-11-21</td>\n    </tr>\n  </tbody>\n</table>\n</div>"]}}],"execution_count":0},{"cell_type":"code","source":[""],"metadata":{"application/vnd.databricks.v1+cell":{"title":"","showTitle":false,"inputWidgets":{},"nuid":"b238a91a-46a8-4189-a0db-229e482b48f7"}},"outputs":[],"execution_count":0}],"metadata":{"application/vnd.databricks.v1+notebook":{"notebookName":"Plotting My Area Lab","dashboards":[],"language":"python","widgets":{},"notebookOrigID":4179985937936567}},"nbformat":4,"nbformat_minor":0}
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		{"cells":[{"cell_type":"markdown","source":["## Plotting My Area\n\nUse the starter code below to explore the data for your area"],"metadata":{}},{"cell_type":"code","source":["import datetime\nimport glob\nimport pandas as pd\n\npath = \"/dbfs/databricks-datasets/COVID/CSSEGISandData/csse_covid_19_data/csse_covid_19_daily_reports\"\nall_files = glob.glob(path + \"/*.csv\")\n\ndfs = []\n\nfor filename in all_files:\n temp_df = pd.read_csv(filename)\n temp_df.columns = [c.replace(\"/\", \"_\") for c in temp_df.columns]\n temp_df.columns = [c.replace(\" \", \"_\") for c in temp_df.columns]\n \n month, day, year = filename.split(\"/\")[-1].replace(\".csv\", \"\").split(\"-\")\n d = datetime.date(int(year), int(month), int(day))\n temp_df[\"Date\"] = d\n\n dfs.append(temp_df)\n \nall_days_df = pd.concat(dfs, axis=0, ignore_index=True, sort=False)\nall_days_df = all_days_df.drop([\"Latitude\", \"Longitude\", \"Lat\", \"Long_\", \"FIPS\", \"Combined_Key\", \"Last_Update\"], axis=1)\n\nall_days_df.head(10)"],"metadata":{},"outputs":[{"metadata":{},"output_type":"display_data","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>Province_State</th>\n <th>Country_Region</th>\n <th>Confirmed</th>\n <th>Deaths</th>\n <th>Recovered</th>\n <th>Date</th>\n <th>Admin2</th>\n <th>Active</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>Anhui</td>\n <td>Mainland China</td>\n <td>1.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020-01-22</td>\n <td>NaN</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>1</th>\n <td>Beijing</td>\n <td>Mainland China</td>\n <td>14.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020-01-22</td>\n <td>NaN</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>2</th>\n <td>Chongqing</td>\n <td>Mainland China</td>\n <td>6.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020-01-22</td>\n <td>NaN</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>3</th>\n <td>Fujian</td>\n <td>Mainland China</td>\n <td>1.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020-01-22</td>\n <td>NaN</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>4</th>\n <td>Gansu</td>\n <td>Mainland China</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020-01-22</td>\n <td>NaN</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>5</th>\n <td>Guangdong</td>\n <td>Mainland China</td>\n <td>26.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020-01-22</td>\n <td>NaN</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>6</th>\n <td>Guangxi</td>\n <td>Mainland China</td>\n <td>2.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020-01-22</td>\n <td>NaN</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>7</th>\n <td>Guizhou</td>\n <td>Mainland China</td>\n <td>1.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020-01-22</td>\n <td>NaN</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>8</th>\n <td>Hainan</td>\n <td>Mainland China</td>\n <td>4.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020-01-22</td>\n <td>NaN</td>\n <td>NaN</td>\n </tr>\n <tr>\n <th>9</th>\n <td>Hebei</td>\n <td>Mainland China</td>\n <td>1.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020-01-22</td>\n <td>NaN</td>\n <td>NaN</td>\n </tr>\n </tbody>\n</table>\n</div>"]}}],"execution_count":2},{"cell_type":"code","source":[""],"metadata":{},"outputs":[],"execution_count":3}],"metadata":{"name":"Plotting My Area Lab","notebookId":17365945},"nbformat":4,"nbformat_minor":0}
		{"cells":[{"cell_type":"markdown","source":["## Plotting My Area\n\nUse the starter code below to explore the data for your area"],"metadata":{"application/vnd.databricks.v1+cell":{"title":"","showTitle":false,"inputWidgets":{},"nuid":"6ac80b32-96fe-419b-8de0-78435d8152e4"}}},{"cell_type":"code","source":["src_path_base = \"dbfs:/databricks-datasets/COVID/CSSEGISandData/csse_covid_19_data/csse_covid_19_daily_reports/\"\ndest_path_base = \"file:////tmp/covid_daily_reports/\"\n\nfiles = [\n '11-21-2020.csv',\n '11-22-2020.csv',\n '11-23-2020.csv',\n '11-24-2020.csv',\n '11-25-2020.csv',\n '11-26-2020.csv',\n '11-27-2020.csv',\n '11-28-2020.csv',\n '11-29-2020.csv',\n '11-30-2020.csv'\n]\n\nall_files = []\n\nfor file in files:\n filename = dest_path_base+file\n dbutils.fs.cp(src_path_base+file, filename)\n all_files.append(filename)\n\nall_files"],"metadata":{"application/vnd.databricks.v1+cell":{"title":"","showTitle":false,"inputWidgets":{},"nuid":"7698baa0-81eb-476b-811c-8367680430eb"}},"outputs":[{"output_type":"display_data","metadata":{"application/vnd.databricks.v1+output":{"datasetInfos":[],"data":"<div class=\"ansiout\">Out[3]: ['file:////tmp/covid_daily_reports/11-21-2020.csv',\n 'file:////tmp/covid_daily_reports/11-22-2020.csv',\n 'file:////tmp/covid_daily_reports/11-23-2020.csv',\n 'file:////tmp/covid_daily_reports/11-24-2020.csv',\n 'file:////tmp/covid_daily_reports/11-25-2020.csv',\n 'file:////tmp/covid_daily_reports/11-26-2020.csv',\n 'file:////tmp/covid_daily_reports/11-27-2020.csv',\n 'file:////tmp/covid_daily_reports/11-28-2020.csv',\n 'file:////tmp/covid_daily_reports/11-29-2020.csv',\n 'file:////tmp/covid_daily_reports/11-30-2020.csv']</div>","removedWidgets":[],"addedWidgets":{},"type":"html","arguments":{}}},"output_type":"display_data","data":{"text/html":["<style scoped>\n .ansiout {\n display: block;\n unicode-bidi: embed;\n white-space: pre-wrap;\n word-wrap: break-word;\n word-break: break-all;\n font-family: \"Source Code Pro\", \"Menlo\", monospace;;\n font-size: 13px;\n color: #555;\n margin-left: 4px;\n line-height: 19px;\n }\n</style>\n<div class=\"ansiout\">Out[3]: ['file:////tmp/covid_daily_reports/11-21-2020.csv',\n 'file:////tmp/covid_daily_reports/11-22-2020.csv',\n 'file:////tmp/covid_daily_reports/11-23-2020.csv',\n 'file:////tmp/covid_daily_reports/11-24-2020.csv',\n 'file:////tmp/covid_daily_reports/11-25-2020.csv',\n 'file:////tmp/covid_daily_reports/11-26-2020.csv',\n 'file:////tmp/covid_daily_reports/11-27-2020.csv',\n 'file:////tmp/covid_daily_reports/11-28-2020.csv',\n 'file:////tmp/covid_daily_reports/11-29-2020.csv',\n 'file:////tmp/covid_daily_reports/11-30-2020.csv']</div>"]}}],"execution_count":0},{"cell_type":"code","source":["import datetime\nimport pandas as pd\n\ndfs = []\n\nfor filename in all_files:\n temp_df = pd.read_csv(filename)\n temp_df.columns = [c.replace(\"/\", \"_\") for c in temp_df.columns]\n temp_df.columns = [c.replace(\" \", \"_\") for c in temp_df.columns]\n \n month, day, year = filename.split(\"/\")[-1].replace(\".csv\", \"\").split(\"-\")\n d = datetime.date(int(year), int(month), int(day))\n temp_df[\"Date\"] = d\n\n dfs.append(temp_df)\n \nall_days_df = pd.concat(dfs, axis=0, ignore_index=True, sort=False)\nall_days_df = all_days_df.drop([\"Lat\", \"Long_\", \"FIPS\", \"Combined_Key\", \"Last_Update\"], axis=1)\n\nall_days_df.head(10)"],"metadata":{"application/vnd.databricks.v1+cell":{"title":"","showTitle":false,"inputWidgets":{},"nuid":"0c71a076-4e9e-434c-97b4-75bc5fceff57"}},"outputs":[{"output_type":"display_data","metadata":{"application/vnd.databricks.v1+output":{"datasetInfos":[],"data":"<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>Admin2</th>\n <th>Province_State</th>\n <th>Country_Region</th>\n <th>Confirmed</th>\n <th>Deaths</th>\n <th>Recovered</th>\n <th>Active</th>\n <th>Incident_Rate</th>\n <th>Case_Fatality_Ratio</th>\n <th>Date</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Afghanistan</td>\n <td>44503</td>\n <td>1675</td>\n <td>35422</td>\n <td>7406.0</td>\n <td>114.320310</td>\n <td>3.763791</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>1</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Albania</td>\n <td>32196</td>\n <td>685</td>\n <td>15469</td>\n <td>16042.0</td>\n <td>1118.771284</td>\n <td>2.127593</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>2</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Algeria</td>\n <td>73774</td>\n <td>2255</td>\n <td>48183</td>\n <td>23336.0</td>\n <td>168.237732</td>\n <td>3.056632</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>3</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Andorra</td>\n <td>6207</td>\n <td>76</td>\n <td>5290</td>\n <td>841.0</td>\n <td>8033.391574</td>\n <td>1.224424</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>4</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Angola</td>\n <td>14413</td>\n <td>336</td>\n <td>7273</td>\n <td>6804.0</td>\n <td>43.853473</td>\n <td>2.331229</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>5</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Antigua and Barbuda</td>\n <td>139</td>\n <td>4</td>\n <td>128</td>\n <td>7.0</td>\n <td>141.941018</td>\n <td>2.877698</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>6</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Argentina</td>\n <td>1366182</td>\n <td>36902</td>\n <td>1187053</td>\n <td>142227.0</td>\n <td>3022.808967</td>\n <td>2.701104</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>7</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Armenia</td>\n <td>124839</td>\n <td>1931</td>\n <td>92829</td>\n <td>30079.0</td>\n <td>4212.930872</td>\n <td>1.546792</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>8</th>\n <td>NaN</td>\n <td>Australian Capital Territory</td>\n <td>Australia</td>\n <td>115</td>\n <td>3</td>\n <td>111</td>\n <td>1.0</td>\n <td>26.862883</td>\n <td>2.608696</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>9</th>\n <td>NaN</td>\n <td>New South Wales</td>\n <td>Australia</td>\n <td>4538</td>\n <td>53</td>\n <td>3173</td>\n <td>1312.0</td>\n <td>55.900468</td>\n <td>1.167915</td>\n <td>2020-11-21</td>\n </tr>\n </tbody>\n</table>\n</div>","textData":"<div class=\"ansiout\">Out[5]: </div>","removedWidgets":[],"addedWidgets":{},"type":"htmlSandbox","arguments":{}}},"output_type":"display_data","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>Admin2</th>\n <th>Province_State</th>\n <th>Country_Region</th>\n <th>Confirmed</th>\n <th>Deaths</th>\n <th>Recovered</th>\n <th>Active</th>\n <th>Incident_Rate</th>\n <th>Case_Fatality_Ratio</th>\n <th>Date</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Afghanistan</td>\n <td>44503</td>\n <td>1675</td>\n <td>35422</td>\n <td>7406.0</td>\n <td>114.320310</td>\n <td>3.763791</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>1</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Albania</td>\n <td>32196</td>\n <td>685</td>\n <td>15469</td>\n <td>16042.0</td>\n <td>1118.771284</td>\n <td>2.127593</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>2</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Algeria</td>\n <td>73774</td>\n <td>2255</td>\n <td>48183</td>\n <td>23336.0</td>\n <td>168.237732</td>\n <td>3.056632</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>3</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Andorra</td>\n <td>6207</td>\n <td>76</td>\n <td>5290</td>\n <td>841.0</td>\n <td>8033.391574</td>\n <td>1.224424</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>4</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Angola</td>\n <td>14413</td>\n <td>336</td>\n <td>7273</td>\n <td>6804.0</td>\n <td>43.853473</td>\n <td>2.331229</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>5</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Antigua and Barbuda</td>\n <td>139</td>\n <td>4</td>\n <td>128</td>\n <td>7.0</td>\n <td>141.941018</td>\n <td>2.877698</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>6</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Argentina</td>\n <td>1366182</td>\n <td>36902</td>\n <td>1187053</td>\n <td>142227.0</td>\n <td>3022.808967</td>\n <td>2.701104</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>7</th>\n <td>NaN</td>\n <td>NaN</td>\n <td>Armenia</td>\n <td>124839</td>\n <td>1931</td>\n <td>92829</td>\n <td>30079.0</td>\n <td>4212.930872</td>\n <td>1.546792</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>8</th>\n <td>NaN</td>\n <td>Australian Capital Territory</td>\n <td>Australia</td>\n <td>115</td>\n <td>3</td>\n <td>111</td>\n <td>1.0</td>\n <td>26.862883</td>\n <td>2.608696</td>\n <td>2020-11-21</td>\n </tr>\n <tr>\n <th>9</th>\n <td>NaN</td>\n <td>New South Wales</td>\n <td>Australia</td>\n <td>4538</td>\n <td>53</td>\n <td>3173</td>\n <td>1312.0</td>\n <td>55.900468</td>\n <td>1.167915</td>\n <td>2020-11-21</td>\n </tr>\n </tbody>\n</table>\n</div>"]}}],"execution_count":0},{"cell_type":"code","source":[""],"metadata":{"application/vnd.databricks.v1+cell":{"title":"","showTitle":false,"inputWidgets":{},"nuid":"b238a91a-46a8-4189-a0db-229e482b48f7"}},"outputs":[],"execution_count":0}],"metadata":{"application/vnd.databricks.v1+notebook":{"notebookName":"Plotting My Area Lab","dashboards":[],"language":"python","widgets":{},"notebookOrigID":4179985937936567}},"nbformat":4,"nbformat_minor":0}