|
|
|
@ -220,7 +220,7 @@
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"# Analise distributon\n",
|
|
|
|
|
"# Analise distribution\n",
|
|
|
|
|
"df.hist(figsize=(10,10))\n",
|
|
|
|
|
"plt.show()"
|
|
|
|
|
]
|
|
|
|
@ -233,7 +233,7 @@
|
|
|
|
|
"source": [
|
|
|
|
|
"# We can see the pairwise correlation between variables. A value near 0 means low correlation\n",
|
|
|
|
|
"# while a value near -1 or 1 indicates strong correlation.\n",
|
|
|
|
|
"df.corr()"
|
|
|
|
|
"df.corr(numeric_only = True)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
@ -249,11 +249,10 @@
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"# General description of relationship betweek variables uwing Seaborn PairGrid\n",
|
|
|
|
|
"# General description of relationship between variables uwing Seaborn PairGrid\n",
|
|
|
|
|
"# We use df_clean, since the null values of df would gives us an error, you can check it.\n",
|
|
|
|
|
"g = sns.PairGrid(df_clean, hue=\"Survived\")\n",
|
|
|
|
|
"g.map_diag(plt.hist)\n",
|
|
|
|
|
"g.map_offdiag(plt.scatter)\n",
|
|
|
|
|
"g.map(sns.scatterplot)\n",
|
|
|
|
|
"g.add_legend()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|