#🐍 #Python #EDA #NaN #ランキング形式

nan_rank.py

def nan_rank(df,  usabilty=20):
    """
    df : データフレーム
    usabilty : データの割合に応じての足切りライン
    """
    nan = df.isnull().sum().reset_index()
    nan.columns = ["name", "count"]
    nan["ratio"] = (nan["count"] / df.shape[0])*100
    nan["usabilty"] = np.where(nan["ratio"] > usabilty, "Discard", "Keep")
    nan = nan[nan["count"] > 0].sort_values(by="ratio")
    
    plt.figure(figsize=(15, 6))
    sns.barplot(x=nan["name"], y=nan["ratio"])
    plt.xticks(rotation=90) #90°傾け
    plt.title("Feature containing NaN.")
    plt.show()
    return nan