diff --git a/model.py b/model.py index b9079bd09840489fdf9e51c73e96b4df1ca7c078..47326fc6879e70ccc97a8a2fc773bf15a1db86b2 100644 --- a/model.py +++ b/model.py @@ -55,4 +55,16 @@ data['Day'] = data["Date"].dt.day # information about data print(data.info()) -print(data["OrderDemand"].describe()) \ No newline at end of file +print(data["OrderDemand"].describe()) + +# information about categorical variables +print(data[["ProductCode", "Warehouse", "ProductCategory"]].describe()) + +# Number of samples according to ProductCategory +plt.figure() +plt.barh(data["ProductCategory"].value_counts().index, data["ProductCategory"].value_counts(), color = "b") +plt.xlabel("Frequency") +plt.ylabel("Product Category") +plt.title("Product Category - Data Frequency") +plt.show() +print(f"Number of ProductCategory \n{data['ProductCategory'].value_counts()}")