initial commit

Untitled-1.ipynb

@@ -0,0 +1,19 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

app.py

@@ -0,0 +1,93 @@
+import streamlit as st
+import pandas as pd 
+import numpy as np 
+import matplotlib.pyplot as plt 
+from statsmodels.tsa.stattools import adfuller
+from statsmodels.tsa.api import ExponentialSmoothing, SimpleExpSmoothing, Holt
+from sklearn.metrics import mean_squared_error, mean_absolute_error
+from math import sqrt
+
+data= pd.read_csv('sample_dataset_timeseries_noarea.csv')
+#menggunakan dictionary untuk menyimpan tabel dari setiap product
+def table_generator(df, listname):
+    name={}
+    n= len(listname)
+    for i in range(n):
+       name[i]=df[df['product_item']==listname[i]]
+    return name
+# menghitung berapa banyak kejadian pembelian setiap produk
+value_counts= data['product_item'].value_counts()
+
+#membuat tabel baru dengan hanya produk yang dibeli di seluruh minggu
+tabel_baru = data.loc[data['product_item'].isin(value_counts[value_counts == 67].index)]
+
+# Kelompokkan data berdasarkan product_item dan hitung total quantity
+grouped_data = tabel_baru.groupby('product_item')['quantity'].sum()
+
+# Urutkan data secara menurun berdasarkan total quantity
+sorted_data = grouped_data.sort_values(ascending=False)
+
+# Ambil product_item dengan total quantity terbanyak
+top_product_item = sorted_data.index[0]
+
+sorted_data2= sorted_data.head(10)
+
+product_item_names = sorted_data2.index.tolist()
+new_data = data[data['product_item'].isin(product_item_names)]
+name= table_generator(data, product_item_names)
+week= new_data.groupby('week_number')['quantity'].sum()
+# Ubah series menjadi dataframe
+df = week.to_frame().reset_index()
+
+# Ganti nama kolom dari indeks menjadi 'Week Number'
+week = df.rename(columns={'index': 'Week Number'})
+#splitting train and test
+train=week[0:53] 
+test=week[53:]
+y_hat_avg = test.copy()
+fit1 = ExponentialSmoothing(np.asarray(train['quantity']), seasonal_periods=13, trend='multiplicative', seasonal='multiplicative').fit()
+y_hat_avg['Holt_Winter'] = fit1.forecast(len(test))
+
+# Create the plot
+fig, ax = plt.subplots(figsize=(20, 8))
+ax.plot(train['quantity'], label='Train')
+ax.plot(test['quantity'], label='Test')
+ax.plot(y_hat_avg['Holt_Winter'], label='Holt_Winter')
+ax.legend(loc='best')
+
+# Show the plot in Streamlit
+st.pyplot(fig)
+
+def forecasting(x):
+    predict= fit1.forecast(len(test)+x)
+    predict= predict[-x:]
+    rounded_arr = []
+    for num in predict:
+        rounded_num = round(num)
+        rounded_arr.append(rounded_num)
+    return rounded_arr
+number = st.number_input("Enter a number between 1 and 10 to predict upcoming weeks", min_value=1, max_value=10)
+num=forecasting(number)
+st.write(num)
+num1 = st.number_input("forecast a product", min_value=0, max_value=9)
+def holtz_generator(df):
+    df=df.drop(columns=['week_start_date','week_end_date','product_item'])
+    n=0.8*len(df)
+    n=round(n)
+    #splitting train and test
+    train=df.iloc[0:n] 
+    test=df.iloc[n:]
+
+    y_hat_avg = test
+    fit1 = ExponentialSmoothing(np.asarray(train['quantity']) ,seasonal_periods=8 ,trend='multiplicative', seasonal='multiplicative').fit()
+    y_hat_avg['Holt_Winter'] = fit1.forecast(len(test))
+    # Create the plot
+    fig, ax = plt.subplots(figsize=(20, 8))
+    ax.plot(train['quantity'], label='Train')
+    ax.plot(test['quantity'], label='Test')
+    ax.plot(y_hat_avg['Holt_Winter'], label='Holt_Winter')
+    ax.legend(loc='best')
+    # Show the plot in Streamlit
+    st.pyplot(fig)
+
+holtz_generator(name[num1])

requirements.txt

@@ -0,0 +1,9 @@
+matplotlib==3.5.2
+numpy==1.21.5
+numpy==1.18.0
+numpy==1.20.0
+pandas==1.4.4
+scikit_learn==1.0.2
+statsmodels==0.13.2
+streamlit==1.21.0
+~treamlit==1.20.0