fix scipy2019 slides ruff

pyjanitor-devs · Sep 7, 2024 · de3f958 · de3f958
1 parent 8c4384d
commit de3f958
Showing 1 changed file with 29 additions and 28 deletions.
diff --git a/talks/scipy2019/slides.ipynb b/talks/scipy2019/slides.ipynb
@@ -398,8 +398,8 @@
     }
    ],
    "source": [
-    "from pyprojroot import here\n",
     "import pandas as pd\n",
+    "from pyprojroot import here\n",
     "\n",
     "df = pd.read_excel(here() / \"examples/notebooks/dirty_data.xlsx\")\n",
     "df\n",
@@ -1142,22 +1142,17 @@
     }
    ],
    "source": [
-    "import datetime as dt \n",
+    "import datetime as dt\n",
     "\n",
     "# Get the \"hire date\" into shape.\n",
-    "df[\"hire_date\"] = (\n",
-    "    pd.TimedeltaIndex(df[\"hire_date\"], unit=\"d\") \n",
-    "    + dt.datetime(1899, 12, 30)\n",
+    "df[\"hire_date\"] = pd.TimedeltaIndex(df[\"hire_date\"], unit=\"d\") + dt.datetime(\n",
+    "    1899, 12, 30\n",
     ")\n",
     "\n",
-    "# Those certification columns don't look particularly good. Should just have one of them. \n",
-    "df['certification'] = df['certification'].combine_first(df['Certification.1'])\n",
-    "df = (\n",
-    "    df\n",
-    "    .drop(\n",
-    "        [\"Certification.1\", \"Certification.2\"], \n",
-    "        axis=1\n",
-    "    )\n",
+    "# Those certification columns don't look particularly good.\n",
+    "# Should just have one of them.\n",
+    "df[\"certification\"] = df[\"certification\"].combine_first(df[\"Certification.1\"])\n",
+    "df = df.drop([\"Certification.1\", \"Certification.2\"], axis=1)\n",
     "df\n",
     "\n",
     "# Next problem: Missing a column"
@@ -1389,9 +1384,13 @@
     }
    ],
    "source": [
-    "# Add a column for \"gratitude points\" given by students to the teachers.\n",
+    "# Add a column for \"gratitude points\"\n",
+    "# given by students to the teachers.\n",
+    "\n",
     "gratitude_points = [10, 50, 20, 1000, 392, 115, 12, 182, 1190, 582, 25, 317]\n",
+    "\n",
     "df = df.assign(gratitude_points=gratitude_points)\n",
+    "\n",
     "df\n",
     "\n",
     "# Next problem: Might want to log-transform."
@@ -1653,7 +1652,9 @@
     "import numpy as np\n",
     "\n",
     "# Finally, log10 transform the gratitude_points column.\n",
+    "\n",
     "df[\"gratitude_points_log\"] = df[\"gratitude_points\"].apply(np.log10)\n",
+    "\n",
     "df\n",
     "\n",
     "# So what does this code look like in totality?"
@@ -1672,7 +1673,8 @@
     "df = (\n",
     "    pd.read_excel(\"../../examples/notebooks/dirty_data.xlsx\")\n",
     "    # Remove the empty column and empty row\n",
-    "    .drop(\"do not edit! --->\", axis=1).drop(7, axis=0)\n",
+    "    .drop(\"do not edit! --->\", axis=1)\n",
+    "    .drop(7, axis=0)\n",
     "    .rename(\n",
     "        mapper={\n",
     "            \"First Name\": \"first_name\",\n",
@@ -1684,16 +1686,17 @@
     "            \"Full time?\": \"full_time\",\n",
     "            \"Certification\": \"certification\",\n",
     "        },\n",
-    "        axis=1\n",
+    "        axis=1,\n",
     "    )\n",
     ")\n",
     "# Correct hire date.\n",
-    "df[\"hire_date\"] = pd.TimedeltaIndex(df[\"hire_date\"], unit=\"d\") + dt.datetime(1899, 12, 30)\n",
+    "df[\"hire_date\"] = pd.TimedeltaIndex(df[\"hire_date\"], unit=\"d\") + dt.datetime(\n",
+    "    1899, 12, 30\n",
+    ")\n",
     "# Squash certification columns\n",
-    "df['certification'] = df['certification'].combine_first(df['Certification.1'])\n",
+    "df[\"certification\"] = df[\"certification\"].combine_first(df[\"Certification.1\"])\n",
     "df = (\n",
-    "    df\n",
-    "    .drop([\"Certification.1\", \"Certification.2\"], axis=1)\n",
+    "    df.drop([\"Certification.1\", \"Certification.2\"], axis=1)\n",
     "    # Add gratidude points.\n",
     "    .assign(gratitude_points=gratitude_points)\n",
     ")\n",
@@ -1759,7 +1762,6 @@
    },
    "outputs": [],
    "source": [
-    "import janitor\n",
     "# Yes, the import name is \"janitor\", \n",
     "# but the package is \"pyjanitor\""
    ]
@@ -2133,10 +2135,11 @@
    },
    "outputs": [],
    "source": [
-    "import pandas_flavor as pf\n",
-    "from numbers import Number\n",
     "from functools import partial\n",
     "\n",
+    "import pandas_flavor as pf\n",
+    "\n",
+    "\n",
     "@pf.register_dataframe_method\n",
     "def log_transform(df, column_name, base, dest_column_name=None):\n",
     "    \"\"\"\n",
@@ -2726,7 +2729,6 @@
     }
    ],
    "source": [
-    "import janitor.biology\n",
     "\n",
     "sequences = (\n",
     "    pd.read_csv(here() / \"tests/test_data/sequences.tsv\", sep=\"\\t\")\n",
@@ -2845,7 +2847,6 @@
     }
    ],
    "source": [
-    "import janitor.chemistry\n",
     "\n",
     "smiles = (\n",
     "    pd.read_csv(here() / \"tests/test_data/corrected_smiles.txt\", sep=\"\\t\", header=None)\n",
@@ -3154,9 +3155,9 @@
  "metadata": {
   "celltoolbar": "Slideshow",
   "kernelspec": {
-   "display_name": "pyjanitor-dev",
+   "display_name": "base",
    "language": "python",
-   "name": "pyjanitor-dev"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -3168,7 +3169,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.9.16"
   },
   "rise": {
    "enable_chalkboard": true,