Merge pull request #199 from realpython/pandas-intro-MNL-fix

pandas-intro: fix MNL example

Author: bzaczynski

pandas-intro/pandas_intro.ipynb

@@ -25,15 +25,15 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Installing Pandas"
+    "### Installing Dependencies"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "```console\n",
-    "$ python -m pip install pandas\n",
+    "$ python3 -m pip install requests pandas matplotlib\n",
     "```"
    ]
   },
@@ -42,7 +42,7 @@
    "metadata": {},
    "source": [
     "```console\n",
-    "$ conda install pandas\n",
+    "$ conda install requests pandas matplotlib\n",
     "```"
    ]
   },
@@ -197,7 +197,7 @@
    "outputs": [],
    "source": [
     "import numpy as np\n",
-    "nba.describe(include=np.object)"
+    "nba.describe(include=object)"
    ]
   },
   {
@@ -230,12 +230,11 @@
    "source": [
     "nba[\"fran_id\"].value_counts()\n",
     "# Expected:\n",
-    "# Name: team_id, Length: 104, dtype: int64\n",
     "# Lakers          6024\n",
     "# Celtics         5997\n",
     "# Knicks          5769\n",
     "\n",
-    "# Huskies           60\n",
+    "# Falcons           60\n",
     "# Name: fran_id, dtype: int64"
    ]
   },
@@ -258,9 +257,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "nba.loc[nba[\"team_id\"] == \"MNL\", \"date_game\"].min()\n",
+    "nba[\"date_played\"] = pd.to_datetime(nba[\"date_game\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nba.loc[nba[\"team_id\"] == \"MNL\", \"date_played\"].min()\n",
     "# Expected:\n",
-    "# '1/1/1949'"
+    "# Timestamp('1948-11-04 00:00:00')"
    ]
   },
   {
@@ -269,9 +277,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "nba.loc[nba[\"team_id\"] == \"MNL\", \"date_game\"].max()\n",
+    "nba.loc[nba[\"team_id\"] == \"MNL\", \"date_played\"].max()\n",
     "# Expected:\n",
-    "# '4/9/1959'"
+    "# Timestamp('1960-03-26 00:00:00')"
    ]
   },
   {
@@ -280,11 +288,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "nba.loc[nba[\"team_id\"] == \"MNL\", \"date_game\"].agg((\"min\", \"max\"))\n",
+    "nba.loc[nba[\"team_id\"] == \"MNL\", \"date_played\"].agg((\"min\", \"max\"))\n",
     "# Expected:\n",
-    "# min    1/1/1949\n",
-    "# max    4/9/1959\n",
-    "# Name: date_game, dtype: object"
+    "# min   1948-11-04\n",
+    "# max   1960-03-26\n",
+    "# Name: date_played, dtype: datetime64[ns]"
    ]
   },
   {
@@ -475,8 +483,8 @@
     "city_data.values\n",
     "# Expected:\n",
     "# array([[4.2e+03, 5.0e+00],\n",
-    "# [6.5e+03, 8.0e+00],\n",
-    "# [8.0e+03,     nan]])"
+    "#        [6.5e+03, 8.0e+00],\n",
+    "#        [8.0e+03,     nan]])"
    ]
   },
   {
@@ -913,7 +921,7 @@
     "current_decade = nba[nba[\"year_id\"] > 2010]\n",
     "current_decade.shape\n",
     "# Expected:\n",
-    "# (12658, 23)"
+    "# (12658, 24)"
    ]
   },
   {
@@ -925,7 +933,7 @@
     "games_with_notes = nba[nba[\"notes\"].notnull()]\n",
     "games_with_notes.shape\n",
     "# Expected:\n",
-    "# (5424, 23)"
+    "# (5424, 24)"
    ]
   },
   {
@@ -937,7 +945,7 @@
     "ers = nba[nba[\"fran_id\"].str.endswith(\"ers\")]\n",
     "ers.shape\n",
     "# Expected:\n",
-    "# (27797, 23)"
+    "# (27797, 24)"
    ]
   },
   {
@@ -1102,7 +1110,7 @@
     "df = nba.copy()\n",
     "df.shape\n",
     "# Expected:\n",
-    "# (126314, 23)"
+    "# (126314, 24)"
    ]
   },
   {
@@ -1121,7 +1129,7 @@
     "df[\"difference\"] = df.pts - df.opp_pts\n",
     "df.shape\n",
     "# Expected:\n",
-    "# (126314, 24)"
+    "# (126314, 25)"
    ]
   },
   {
@@ -1155,16 +1163,17 @@
     "# Expected:\n",
     "# <class 'pandas.core.frame.DataFrame'>\n",
     "# RangeIndex: 126314 entries, 0 to 126313\n",
-    "# Data columns (total 24 columns):\n",
+    "# Data columns (total 25 columns):\n",
     "# gameorder      126314 non-null int64\n",
     "\n",
     "# location       126314 non-null object\n",
     "# result         126314 non-null object\n",
     "# forecast       126314 non-null float64\n",
     "# notes          5424 non-null object\n",
+    "# date_played    126314 non-null datetime64[ns]\n",
     "# difference     126314 non-null int64\n",
-    "# dtypes: float64(6), int64(8), object(10)\n",
-    "# memory usage: 23.1+ MB"
+    "# dtypes: datetime64[ns](1), float64(6), int64(8), object(10)\n",
+    "# memory usage: 24.1+ MB"
    ]
   },
   {
@@ -1182,7 +1191,7 @@
    "source": [
     "df.shape\n",
     "# Expected:\n",
-    "# (126314, 24)"
+    "# (126314, 25)"
    ]
   },
   {
@@ -1195,7 +1204,7 @@
     "df.drop(elo_columns, inplace=True, axis=1)\n",
     "df.shape\n",
     "# Expected:\n",
-    "# (126314, 20)"
+    "# (126314, 21)"
    ]
   },
   {
@@ -1301,7 +1310,7 @@
     "rows_without_missing_data = nba.dropna()\n",
     "rows_without_missing_data.shape\n",
     "# Expected:\n",
-    "# (5424, 23)"
+    "# (5424, 24)"
    ]
   },
   {
@@ -1313,7 +1322,7 @@
     "data_without_missing_columns = nba.dropna(axis=1)\n",
     "data_without_missing_columns.shape\n",
     "# Expected:\n",
-    "# (126314, 22)"
+    "# (126314, 23)"
    ]
   },
   {
@@ -1541,22 +1550,24 @@
  ],
  "metadata": {
   "kernelspec": {
-   "argv": [
-    "/home/reka/anaconda3/bin/python",
-    "-m",
-    "ipykernel_launcher",
-    "-f",
-    "{connection_file}"
-   ],
    "display_name": "Python 3",
-   "env": {},
-   "interrupt_mode": "signal",
    "language": "python",
-   "metadata": {},
    "name": "python3"
   },
-  "language": "python"
+  "language": "python",
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.2"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }