Exemple fillna - afficher les count et std

Author: plstonge

en/03-format.ipynb

@@ -275,9 +275,17 @@
    },
    "outputs": [],
    "source": [
+    "def state_by_species(df, column):\n",
+    "    print(\n",
+    "        df.groupby('species_id')[column].aggregate(\n",
+    "            ['count', 'mean', 'std']\n",
+    "        ).loc['DM':'NL']\n",
+    "    )\n",
+    "    print()\n",
+    "    print('Total count:', df[column].count())\n",
+    "\n",
     "# Before the cleanup\n",
-    "print('Total count :', surveys_df['weight'].count())\n",
-    "surveys_df.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "state_by_species(surveys_df, 'weight')"
    ]
   },
   {
@@ -331,9 +339,10 @@
    },
    "outputs": [],
    "source": [
-    "# After the cleanup\n",
-    "print('Total count :', copy_surveys['weight'].count())\n",
-    "copy_surveys.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "# Before and after the cleanup\n",
+    "state_by_species(surveys_df, 'weight')\n",
+    "print()  # Print an empty line\n",
+    "state_by_species(copy_surveys, 'weight')"
    ]
   },
   {

fr/03-format.ipynb

@@ -275,9 +275,17 @@
    },
    "outputs": [],
    "source": [
+    "def etat_par_species(df, colonne):\n",
+    "    print(\n",
+    "        df.groupby('species_id')[colonne].aggregate(\n",
+    "            ['count', 'mean', 'std']\n",
+    "        ).loc['DM':'NL']\n",
+    "    )\n",
+    "    print()\n",
+    "    print('Décompte total :', df[colonne].count())\n",
+    "\n",
     "# Avant le nettoyage\n",
-    "print('Décompte total :', surveys_df['weight'].count())\n",
-    "surveys_df.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "etat_par_species(surveys_df, 'weight')"
    ]
   },
   {
@@ -331,9 +339,10 @@
    },
    "outputs": [],
    "source": [
-    "# Après le nettoyage\n",
-    "print('Décompte total :', copie_surveys['weight'].count())\n",
-    "copie_surveys.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "# Avant et après le nettoyage\n",
+    "etat_par_species(surveys_df, 'weight')\n",
+    "print()  # Afficher une ligne vide\n",
+    "etat_par_species(copie_surveys, 'weight')"
    ]
   },
   {

solution-en/03-format.ipynb

@@ -275,9 +275,17 @@
    },
    "outputs": [],
    "source": [
+    "def state_by_species(df, column):\n",
+    "    print(\n",
+    "        df.groupby('species_id')[column].aggregate(\n",
+    "            ['count', 'mean', 'std']\n",
+    "        ).loc['DM':'NL']\n",
+    "    )\n",
+    "    print()\n",
+    "    print('Total count:', df[column].count())\n",
+    "\n",
     "# Before the cleanup\n",
-    "print('Total count :', surveys_df['weight'].count())\n",
-    "surveys_df.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "state_by_species(surveys_df, 'weight')"
    ]
   },
   {
@@ -331,9 +339,10 @@
    },
    "outputs": [],
    "source": [
-    "# After the cleanup\n",
-    "print('Total count :', copy_surveys['weight'].count())\n",
-    "copy_surveys.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "# Before and after the cleanup\n",
+    "state_by_species(surveys_df, 'weight')\n",
+    "print()  # Print an empty line\n",
+    "state_by_species(copy_surveys, 'weight')"
    ]
   },
   {

solution-fr/03-format.ipynb

@@ -275,9 +275,17 @@
    },
    "outputs": [],
    "source": [
+    "def etat_par_species(df, colonne):\n",
+    "    print(\n",
+    "        df.groupby('species_id')[colonne].aggregate(\n",
+    "            ['count', 'mean', 'std']\n",
+    "        ).loc['DM':'NL']\n",
+    "    )\n",
+    "    print()\n",
+    "    print('Décompte total :', df[colonne].count())\n",
+    "\n",
     "# Avant le nettoyage\n",
-    "print('Décompte total :', surveys_df['weight'].count())\n",
-    "surveys_df.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "etat_par_species(surveys_df, 'weight')"
    ]
   },
   {
@@ -331,9 +339,10 @@
    },
    "outputs": [],
    "source": [
-    "# Après le nettoyage\n",
-    "print('Décompte total :', copie_surveys['weight'].count())\n",
-    "copie_surveys.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "# Avant et après le nettoyage\n",
+    "etat_par_species(surveys_df, 'weight')\n",
+    "print()  # Afficher une ligne vide\n",
+    "etat_par_species(copie_surveys, 'weight')"
    ]
   },
   {

src/03-format.ipynb

@@ -541,9 +541,17 @@
    },
    "outputs": [],
    "source": [
+    "def etat_par_species(df, colonne):\n",
+    "    print(\n",
+    "        df.groupby('species_id')[colonne].aggregate(\n",
+    "            ['count', 'mean', 'std']\n",
+    "        ).loc['DM':'NL']\n",
+    "    )\n",
+    "    print()\n",
+    "    print('Décompte total :', df[colonne].count())\n",
+    "\n",
     "# Avant le nettoyage\n",
-    "print('Décompte total :', surveys_df['weight'].count())\n",
-    "surveys_df.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "etat_par_species(surveys_df, 'weight')"
    ]
   },
   {
@@ -555,9 +563,17 @@
    },
    "outputs": [],
    "source": [
+    "def state_by_species(df, column):\n",
+    "    print(\n",
+    "        df.groupby('species_id')[column].aggregate(\n",
+    "            ['count', 'mean', 'std']\n",
+    "        ).loc['DM':'NL']\n",
+    "    )\n",
+    "    print()\n",
+    "    print('Total count:', df[column].count())\n",
+    "\n",
     "# Before the cleanup\n",
-    "print('Total count :', surveys_df['weight'].count())\n",
-    "surveys_df.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "state_by_species(surveys_df, 'weight')"
    ]
   },
   {
@@ -653,9 +669,10 @@
    },
    "outputs": [],
    "source": [
-    "# Après le nettoyage\n",
-    "print('Décompte total :', copie_surveys['weight'].count())\n",
-    "copie_surveys.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "# Avant et après le nettoyage\n",
+    "etat_par_species(surveys_df, 'weight')\n",
+    "print()  # Afficher une ligne vide\n",
+    "etat_par_species(copie_surveys, 'weight')"
    ]
   },
   {
@@ -667,9 +684,10 @@
    },
    "outputs": [],
    "source": [
-    "# After the cleanup\n",
-    "print('Total count :', copy_surveys['weight'].count())\n",
-    "copy_surveys.groupby('species_id')['weight'].mean().loc['DM':'NL']"
+    "# Before and after the cleanup\n",
+    "state_by_species(surveys_df, 'weight')\n",
+    "print()  # Print an empty line\n",
+    "state_by_species(copy_surveys, 'weight')"
    ]
   },
   {