Fix errors in Pandas notebook (#194)

empa-scientific-it · Feb 23, 2024 · 1b42590 · 1b42590
1 parent 4a478af
commit 1b42590
Showing 1 changed file with 21 additions and 37 deletions.
diff --git a/library_pandas.ipynb b/library_pandas.ipynb
@@ -1003,7 +1003,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!wc -l data/earthquakes.csv"
+    "!wc -l data/01/earthquakes.csv"
    ]
   },
   {
@@ -1014,7 +1014,7 @@
     "**Windows users**: if the above doesn't work for you (depends on your setup), then use this instead:\n",
     "\n",
     "```python\n",
-    "!find /c /v \"\" data\\earthquakes.csv\n",
+    "!find /c /v \"\" data\\01\\earthquakes.csv\n",
     "```\n",
     "\n",
     "\n",
@@ -1030,7 +1030,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!ls -lh data | grep earthquakes.csv"
+    "!ls -lh data/01 | grep earthquakes.csv"
    ]
   },
   {
@@ -1041,7 +1041,7 @@
     "**Windows users**: if the above doesn't work for you (depends on your setup), then use this instead:\n",
     "\n",
     "```python\n",
-    "!dir data | findstr \"earthquakes.csv\"\n",
+    "!dir data\\01 | findstr \"earthquakes.csv\"\n",
     "```\n",
     "\n",
     "We can even capture the result of a command and use it in our Python code:"
@@ -1054,7 +1054,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "files = !ls -lh data\n",
+    "files = !ls -lh data/01\n",
     "[file for file in files if 'earthquake' in file]"
    ]
   },
@@ -1066,7 +1066,7 @@
     "**Windows users**: if the above doesn't work for you (depends on your setup), then use this instead:\n",
     "\n",
     "```python\n",
-    "files = !dir data\n",
+    "files = !dir data\\01\n",
     "[file for file in files if 'earthquake' in file]\n",
     "```"
    ]
@@ -1088,7 +1088,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!head -n 2 data/earthquakes.csv"
+    "!head -n 2 data/01/earthquakes.csv"
    ]
   },
   {
@@ -1100,7 +1100,7 @@
     "\n",
     "```python\n",
     "n = 2\n",
-    "with open('data/earthquakes.csv', 'r') as file:\n",
+    "with open('data/01/earthquakes.csv', 'r') as file:\n",
     "    for _ in range(n):\n",
     "        print(file.readline(), end='\\r')\n",
     "```\n",
@@ -1116,7 +1116,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!tail -n 1 data/earthquakes.csv"
+    "!tail -n 1 data/01/earthquakes.csv"
    ]
   },
   {
@@ -1129,7 +1129,7 @@
     "```python\n",
     "import os\n",
     "\n",
-    "with open('data/earthquakes.csv', 'rb') as file:\n",
+    "with open('data/01/earthquakes.csv', 'rb') as file:\n",
     "    file.seek(0, os.SEEK_END)\n",
     "    while file.read(1) != b'\\n':\n",
     "        file.seek(-2, os.SEEK_CUR)\n",
@@ -1140,7 +1140,7 @@
     "\n",
     "```python\n",
     "n = 2\n",
-    "with open('data/earthquakes.csv', 'r') as file:\n",
+    "with open('data/01/earthquakes.csv', 'r') as file:\n",
     "    print('\\r'.join(file.readlines()[-n:]))\n",
     "```\n",
     "\n"
@@ -1164,7 +1164,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!awk -F',' '{print NF; exit}' data/earthquakes.csv"
+    "!awk -F',' '{print NF; exit}' data/01/earthquakes.csv"
    ]
   },
   {
@@ -1175,7 +1175,7 @@
     "**Windows users**: if the above or below don't work for you (depends on your setup), then use this instead:\n",
     "\n",
     "```python\n",
-    "with open('data/earthquakes.csv', 'r') as file:\n",
+    "with open('data/01/earthquakes.csv', 'r') as file:\n",
     "    print(len(file.readline().split(',')))\n",
     "```\n",
     "\n",
@@ -1190,7 +1190,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "headers = !head -n 1 data/earthquakes.csv\n",
+    "headers = !head -n 1 data/01/earthquakes.csv\n",
     "len(headers[0].split(','))"
    ]
   },
@@ -1220,7 +1220,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df = pd.read_csv('data/earthquakes.csv')"
+    "df = pd.read_csv('data/01/earthquakes.csv')"
    ]
   },
   {
@@ -2155,24 +2155,6 @@
     "pd.concat([tsunami, no_tsunami]).shape"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "d38495fa-fe5e-4937-9774-b90c0d26e6d9",
-   "metadata": {},
-   "source": [
-    "Note that the previous result is equivalent to running the `append()` method of the dataframe:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "8c6be158-f310-42b7-a05e-cd4b6a6e07b2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tsunami.append(no_tsunami).shape"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "ba559768-6848-4eca-9b84-04b8b6e78417",
@@ -2189,7 +2171,7 @@
    "outputs": [],
    "source": [
     "additional_columns = pd.read_csv(\n",
-    "    'data/earthquakes.csv', usecols=['tz', 'felt', 'ids']\n",
+    "    'data/01/earthquakes.csv', usecols=['tz', 'felt', 'ids']\n",
     ")\n",
     "pd.concat([df.head(2), additional_columns.head(2)], axis=1)"
    ]
@@ -2210,7 +2192,7 @@
    "outputs": [],
    "source": [
     "additional_columns = pd.read_csv(\n",
-    "    'data/earthquakes.csv', usecols=['tz', 'felt', 'ids', 'time'], index_col='time'\n",
+    "    'data/01/earthquakes.csv', usecols=['tz', 'felt', 'ids', 'time'], index_col='time'\n",
     ")\n",
     "pd.concat([df.head(2), additional_columns.head(2)], axis=1)"
    ]
@@ -3618,14 +3600,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "extra_data = long_df.append([{\n",
+    "extra_data = pd.DataFrame([{\n",
     "    'datatype': 'TAVG', \n",
     "    'date': '2018-10-01', \n",
     "    'temp_C': 10, \n",
     "    'temp_F': 50\n",
     "}]).set_index(['date', 'datatype']).sort_index()\n",
     "\n",
-    "extra_data['2018-10-01':'2018-10-02']"
+    "extra_data = pd.concat([long_df, extra_data])\n",
+    "\n",
+    "extra_data.head()"
    ]
   },
   {