Upload files to 'Demand_forcasting'

Demand_forcasting/forcasting.py

@@ -0,0 +1,610 @@
+
+
+
+from flask import Flask, render_template, send_file, request, redirect, Response
+import os
+
+
+import pandas as pd
+import warnings
+import json
+import requests
+from urllib.request import urlopen
+warnings.filterwarnings("ignore")
+
+
+
+
+
+app = Flask(__name__)
+
+
+@app.route("/", methods=["GET"])
+def home():
+    return 'forcasting app running'
+
+######################################################################################################################
+list_output=[]
+
+def day(Num,df):
+
+
+    #url='https://qa.bizgaze.app/apis/v4/bizgaze/integrations/demandforecast/getitemdata'
+    url='https://test.bizgaze.app/apis/v4/bizgaze/integrations/demandforecast/getitemdata'
+    response = urlopen(url)
+    data_json = json.loads(response.read())
+    headers = {
+            'Authorization':'stat 27e6b51b278d444aa0b70ed60419b04c',
+            #'Authorization':'stat 873f2e6f70b3483e983972f96fbf5ea4',#qa
+            'Content-Type': 'application/json'
+    }
+    response = requests.request("GET", url, headers=headers, data=data_json)
+    #print("##############################################################")
+    a=response.text
+    # print(response.text)
+    
+    import pandas as pd
+    
+    df2 = pd.read_json(response.text, orient ='index')
+    df2=df2.reset_index()
+    df2.columns = ['key','value']
+    #print(df2)
+    a=df2['value'][0]
+    
+    j=json.loads(a)
+    userdata = pd.DataFrame(j)
+    #df1
+    itemid=userdata[['itemname','itemid']]
+    itemid.columns = ['ItemName', 'ItemId']
+    
+    #df1=pd.read_csv(r'./upload/' + name)
+    #df1=df1[df1['obdate']!='01/01/0001']
+    userdata.columns = ['journaldate','sum','itemname','itemid']
+    
+    
+    # import pandas as pd
+    # userdata = pd.read_csv(r'C:\Users\Bizga\Desktop\forcast\5yearsitems.csv')
+    # itemid = userdata[['itemname', 'itemid']]
+    #userdata['journaldate'] = pd.to_datetime(userdata['journaldate'])
+    userdata["journaldate"] = userdata["journaldate"].astype(str)
+    userdata[["year", "month", "day"]] = userdata["journaldate"].str.split("/", expand = True)
+    #userdata['Month-Year']=userdata['year'].astype(str)+'-'+userdata['month'].astype(str)
+    item_unique_name = userdata['itemname'].unique()
+    
+    #df=pd.read_csv("C:\\Users\\Bizgaze\\2021_2022.csv")
+    # Group the DataFrame by the 'item' column
+    grouped = userdata.groupby('itemname')
+    
+    # Print the unique items in the 'item' column
+    #print(grouped.groups.keys())
+    
+    # Iterate over the unique items and print the group data
+    for item, userdata in grouped:
+        print("itemname: ", item)
+    
+        item_id = userdata.iloc[-1]['itemid']
+       
+        print(item_id)
+    
+        userdata= userdata.groupby('journaldate').sum()
+        userdata= userdata.reset_index()
+        #print(userdata)
+        fulldata=userdata[['journaldate','sum']]
+        fulldata.columns = ["Dates","SALES"]
+    #************************************************************************************************************************
+    
+        ## Use Techniques Differencing
+        import pandas as pd
+        from pandas import DataFrame
+        
+        # userdata=pd.read_csv(r"C:\Users\Bizgaze\ipynb files\TS forcasting\working\139470.csv")
+        
+        userdata.columns = ['Date', 'sales','sku']
+        from statsmodels.tsa.stattools import adfuller
+        
+        DATE=[]
+        SALES=[]
+        
+        
+        def adf_test(series,userdata):
+            result=adfuller(series)
+            print('ADF Statistics: {}'.format(result[0]))
+            print('p- value: {}'.format(result[1]))
+            if result[1] <= 0.05:
+                print("strong evidence against the null hypothesis, reject the null hypothesis. Data has no unit root and is stationary")
+            else:
+            #print(userdata)
+                print(stationary_test(userdata))
+                print("weak evidence against null hypothesis, time series has a unit root, indicating it is non-stationary ")
+            
+            
+        
+        
+        #*********************************************    stationary or non-stationary **********************************************************   
+        def stationary_test(userdata):
+          data=pd.DataFrame(userdata)
+          for i in range(1,13):
+            print(i)
+            sales_data=DataFrame()
+            data['sales']=data['sales'].shift(i)
+            data.dropna(inplace=True)
+            #print( userdata['sales'])
+            try:
+              X=adf_test(data["sales"],userdata="nothing")
+              if "non-stationary" in str(X):
+                print("non-stationary")
+              else:
+                print("stationary")
+                #print(userdata[["Date","sales"]])
+                #df_sale=pd.DataFrame(userdata)
+                DATE.append(data["Date"])
+                SALES.append(data["sales"])
+                #df4 = pd.concat([data, sales_data], axis=1)
+                return "done"
+                break
+            except ValueError:
+              pass
+        
+        try:
+            adf_test(userdata["sales"],userdata)
+        except ValueError:
+            pass
+        sales=pd.DataFrame(SALES).T
+        dates=pd.DataFrame(DATE).T
+        try:
+            df4 = pd.concat([dates["Date"],sales["sales"]], axis=1)
+            df4=df4.dropna()
+            print(df4)
+        except KeyError:
+            df4=userdata[['Date','sales']]
+            df4=df4.dropna()
+            print(df4)
+            pass
+        
+    #####################################################################################################################  
+        userdata=df4
+        a = userdata.iloc[-1]['Date']
+        userdata['Date'] = pd.to_datetime(userdata['Date'])
+        userdata["Date"] = userdata["Date"].astype(str)
+        userdata[["year", "month", "day"]] = userdata["Date"].str.split("-", expand = True)
+        #userdata[["year", "month"]] = userdata["Month"].str.split("-", expand=True)
+        #userdata = userdata[["year","month",'sum']]
+        userdata["year"] = userdata["year"].astype(int)
+        userdata["month"] = userdata["month"].astype(int)
+        userdata["day"] = userdata["day"].astype(int)
+    #####################################################################################################################
+    
+    
+        list_dates=[]
+        import datetime
+    
+        days=int(Num)+1
+        import pandas as pd
+        base_date=pd.to_datetime(a)
+        for x in range(1,days):
+              dates=(base_date + datetime.timedelta(days=x))
+              dates=str(dates).replace(" 00:00:00","")
+              #print(dates)
+              list_dates.append(dates)
+        fut_date = pd.DataFrame(list_dates)
+        fut_date.columns = ["Dates"]
+        
+        future_dates=pd.DataFrame(list_dates)
+    
+        future_dates.columns=["Dates"]
+        future_dates[["year", "month", "day"]] = future_dates["Dates"].str.split("-", expand=True)
+        future_dates.drop(['Dates'], axis=1, inplace=True)
+        future_dates["year"] = future_dates["year"].astype(int)
+        future_dates["month"] = future_dates["month"].astype(int)
+        future_dates["day"] = future_dates["day"].astype(int)
+        #print(future_dates)
+    
+    
+    
+        ###############################################################################
+        userdata['sales']=userdata["sales"].astype(float)
+        dependent = userdata[['year','month','day']]
+        independent = userdata['sales']
+    
+        import numpy as np
+        import pandas as pd
+    
+        import xgboost
+        from sklearn.model_selection import train_test_split
+        from sklearn.model_selection import GridSearchCV
+        from sklearn.metrics import roc_auc_score
+    
+        import matplotlib.pyplot as plt
+    
+        #model = xgboost.XGBRegressor()
+        from sklearn.ensemble import RandomForestRegressor
+        model = RandomForestRegressor(random_state=1,n_jobs=-1)
+        #model.fit(dependent, independent)
+        model.fit(dependent, independent)
+        #future=pd.read_csv('future_dates.csv')
+    
+    
+        future_prediction = model.predict(future_dates)
+        #print(future_prediction)
+        df=pd.DataFrame(future_prediction)
+        df.columns = ["SALES"]
+        frames = [fut_date, df]
+      
+      
+        result = pd.concat(frames,axis=1)
+        result['itemname'] = item
+        result['itemid'] =item_id 
+        result.columns = ['Date','Predict','ItemName','ItemId']
+        #result['Predict']=result["Predict"].astype(int)
+        result['UpperLimit']=result["Predict"].mean()+result['Predict'].std()*3
+        result['LowerLimit']=result['Predict'].mean()-result['Predict'].std()*3
+        print(result)
+        result.to_json('forcast.json', orient="records")
+        # result['ItemName'] = item
+        # result['ItemId'] =item_id 
+        # print(result)
+        # frames = [fulldata, result]
+      
+        # final = pd.concat(frames)
+        # print('********************************************************')
+        # final['itemname'] = item
+        # final['itemid'] =item_id 
+        # final.columns = ['Date','Predict','ItemName','ItemId']
+        # print(final)
+        # final.to_json('forcast.json', orient="records")
+    
+        with open('forcast.json', 'r') as json_file:
+            json_load = json.load(json_file)
+            #url = "https://demo.bizgaze.app/apis/v4/bizgaze/integrations/demandforecast/saveforecast/List"
+            url='https://qa.bizgaze.app/apis/v4/bizgaze/integrations/demandforecast/saveforecast/List'
+    
+        payload = json.dumps(json_load)#.replace("]", "").replace("[", "")
+        print(payload)
+        headers = {
+            #'Authorization': 'stat 263162e61f084d3392f162eb7ec39b2c',#demo
+            'Authorization': 'stat 873f2e6f70b3483e983972f96fbf5ea4',#test
+            'Content-Type': 'application/json'
+        }
+        response = requests.request("POST", url, headers=headers, data=payload)
+        print("##############################################################")
+        print(response.text)
+    
+    
+       
+    
+        import time
+        time.sleep(1)   
+
+
+#############################################################################################################################################################
+
+
+def month(Num,df):
+
+
+
+    # #url='https://qa.bizgaze.app/apis/v4/bizgaze/integrations/demandforecast/getitemdata'
+    # url='https://test.bizgaze.app/apis/v4/bizgaze/integrations/demandforecast/getitemdata'
+    # response = urlopen(url)
+    # data_json = json.loads(response.read())
+    # headers = {
+    #         'Authorization':'stat 27e6b51b278d444aa0b70ed60419b04c',
+    #         #'Authorization':'stat 873f2e6f70b3483e983972f96fbf5ea4',#qa
+    #         'Content-Type': 'application/json'
+    # }
+    # response = requests.request("GET", url, headers=headers, data=data_json)
+    # #print("##############################################################")
+    # a=response.text
+    
+    
+    # import pandas as pd
+    # df2 = pd.read_json(response.text, orient ='index')
+    # df2=df2.reset_index()
+    # df2.columns = ['key','value']
+    # #print(df2)
+    # a=df2['value'][0]
+    
+    # j=json.loads(a)
+    # userdata = pd.DataFrame(j)
+    # #df1
+    filePath='path.csv'
+    if os.path.exists(filePath):
+        print('file exist')
+        os.remove('path.csv')
+    else:
+        print("file as it doesn't exists")
+        pass
+    userdata=df
+    itemid=userdata[['itemname','itemid']]
+    itemid.columns = ['ItemName', 'ItemId']
+    
+    #df1=pd.read_csv(r'./upload/' + name)
+    #df1=df1[df1['obdate']!='01/01/0001']
+    userdata.columns = ['itemname','sum','journaldate','itemid']
+    # import pandas as pd
+    # userdata = pd.read_csv(r'C:\Users\Bizga\Desktop\forcast\5yearsitems.csv')
+    # itemid = userdata[['itemname', 'itemid']]
+    #userdata['journaldate'] = pd.to_datetime(userdata['journaldate'])
+    userdata["journaldate"] = userdata["journaldate"].astype(str)
+    userdata[["year", "month", "day"]] = userdata["journaldate"].str.split("-", expand = True)
+    userdata['Month-Year']=userdata['year'].astype(str)+'-'+userdata['month'].astype(str)
+    item_unique_name = userdata['itemname'].unique()
+    
+    #df=pd.read_csv("C:\\Users\\Bizgaze\\2021_2022.csv")
+    # Group the DataFrame by the 'item' column
+    grouped = userdata.groupby('itemname')
+    
+    # Print the unique items in the 'item' column
+    #print(grouped.groups.keys())
+    
+    # Iterate over the unique items and print the group data
+    for item, userdata in grouped:
+        print("itemname: ", item)
+    
+        item_id = userdata.iloc[-1]['itemid']
+       
+        print(item_id)
+    
+        userdata= userdata.groupby('Month-Year').sum()
+        userdata= userdata.reset_index()
+        #print(userdata)
+        fulldata=userdata[['Month-Year','sum']]
+        fulldata.columns = ["Dates","SALES"]
+    #************************************************************************************************************************
+    
+        ## Use Techniques Differencing
+        import pandas as pd
+        from pandas import DataFrame
+        
+        # userdata=pd.read_csv(r"C:\Users\Bizgaze\ipynb files\TS forcasting\working\139470.csv")
+        
+        userdata.columns = ['Month', 'sales','sku']
+        from statsmodels.tsa.stattools import adfuller
+        
+        DATE=[]
+        SALES=[]
+        
+        
+        def adf_test(series,userdata):
+            result=adfuller(series)
+            print('ADF Statistics: {}'.format(result[0]))
+            print('p- value: {}'.format(result[1]))
+            if result[1] <= 0.05:
+                print("strong evidence against the null hypothesis, reject the null hypothesis. Data has no unit root and is stationary")
+            else:
+            #print(userdata)
+                print(stationary_test(userdata))
+                print("weak evidence against null hypothesis, time series has a unit root, indicating it is non-stationary ")
+            
+            
+        
+        
+        #*********************************************    stationary or non-stationary **********************************************************   
+        def stationary_test(userdata):
+          data=pd.DataFrame(userdata)
+          for i in range(1,13):
+            print(i)
+            sales_data=DataFrame()
+            data['sales']=data['sales'].shift(i)
+            data.dropna(inplace=True)
+            #print( userdata['sales'])
+            try:
+              X=adf_test(data["sales"],userdata="nothing")
+              if "non-stationary" in str(X):
+                print("non-stationary")
+              else:
+                print("stationary")
+                #print(userdata[["Month","sales"]])
+                #df_sale=pd.DataFrame(userdata)
+                DATE.append(data["Month"])
+                SALES.append(data["sales"])
+                #df4 = pd.concat([data, sales_data], axis=1)
+                return "done"
+                break
+            except ValueError:
+              pass
+        
+        try:
+            adf_test(userdata["sales"],userdata)
+        except ValueError:
+            pass
+        sales=pd.DataFrame(SALES).T
+        dates=pd.DataFrame(DATE).T
+        try:
+            df4 = pd.concat([dates["Month"],sales["sales"]], axis=1)
+            df4=df4.dropna()
+            print(df4)
+        except KeyError:
+            df4=userdata[['Month','sales']]
+            df4=df4.dropna()
+            print(df4)
+            pass
+        
+    #####################################################################################################################  
+        userdata=df4
+        a = userdata.iloc[-1]['Month']
+        userdata[["year", "month"]] = userdata["Month"].str.split("-", expand=True)
+        #userdata = userdata[["year","month",'sum']]
+        userdata["year"] = userdata["year"].astype(int)
+        userdata["month"] = userdata["month"].astype(int)
+    #####################################################################################################################
+    
+        #a = userdata.iloc[-1]['Month-Year']
+        from datetime import datetime
+        from dateutil.relativedelta import relativedelta
+        import pandas as pd
+        months_value = int(Num)+1
+        base_month = pd.to_datetime(a)
+        list_months = []
+        
+        def months(MD):
+            date_after_month = ((base_month + relativedelta(months=MD)).strftime('%Y-%m'))
+            # print
+            list_months.append(date_after_month)
+        
+        for i in range(1, months_value):
+            months(i)
+        
+        future_dates = pd.DataFrame(list_months)
+        
+        future_dates.columns = ["Dates"]
+    
+        fut_date = pd.DataFrame(list_months)
+        fut_date.columns = ["Dates"]
+        
+        future_dates[["year", "month"]] = future_dates["Dates"].str.split("-", expand=True)
+        future_dates.drop(['Dates'], axis=1, inplace=True)
+        future_dates["year"] = future_dates["year"].astype(int)
+        future_dates["month"] = future_dates["month"].astype(int)
+        
+    
+    
+    
+        ###############################################################################
+        userdata['sales']=userdata["sales"].astype(float)
+        dependent = userdata[['year','month']]
+        independent = userdata['sales']
+    
+        import numpy as np
+        import pandas as pd
+    
+        import xgboost
+        from sklearn.model_selection import train_test_split
+        from sklearn.model_selection import GridSearchCV
+        from sklearn.metrics import roc_auc_score
+    
+        import matplotlib.pyplot as plt
+    
+        #model = xgboost.XGBRegressor()
+        from sklearn.ensemble import RandomForestRegressor
+        model = RandomForestRegressor(random_state=1,n_jobs=-1)
+        model.fit(dependent, independent)
+        #future=pd.read_csv('future_dates.csv')
+    
+    
+        future_prediction = model.predict(future_dates)
+        #print(future_prediction)
+        df=pd.DataFrame(future_prediction)
+        df.columns = ["SALES"]
+        frames = [fut_date, df]
+      
+      
+        result = pd.concat(frames,axis=1)
+        result['itemname'] = item
+        result['itemid'] =item_id 
+        result.columns = ['Date','Predict','ItemName','ItemId']
+        #result['Predict']=result["Predict"].astype(int)
+        result['UpperLimit']=result["Predict"].mean()+result['Predict'].std()*3
+        result['LowerLimit']=result['Predict'].mean()-result['Predict'].std()*3
+        result["LowerLimit"][result["LowerLimit"] < 0] = 0
+        print(result)
+        
+        filePath='path.csv'
+
+           
+        if os.path.exists(filePath):
+            print('file exist')
+            #userdata = pd.DataFrame(data)
+            result.to_csv('path.csv', mode='a',index=False, header=False)
+
+        else:
+            print("file as it doesn't exists")
+            #result = pd.DataFrame(data)
+            result.to_csv('path.csv', index=False)
+    
+
+
+    result=pd.read_csv('path.csv')
+    result.to_json('forcast.json', orient="records")
+    import json
+
+    # open the JSON file and read its contents
+    with open(r'forcast.json', 'r') as f:
+        json_data = json.load(f)
+
+    # print the JSON data
+    #print(json_data)
+    
+    #output={"response":"success","result":json_data}
+    #print(output)
+    return json_data
+   
+        # frames = [fulldata, result]
+      
+        # final = pd.concat(frames)
+        # print('********************************************************')
+        # final['itemname'] = item
+        # final['itemid'] =item_id 
+        # final.columns = ['Date','Predict','ItemName','ItemId']
+        # final['upper_limit']=final["Predict"]+final['Predict']*0.2
+        # # final['lower_limit']=final['Predict']-final['Predict']*0.2
+        # # print(final)
+        # # final.to_json('forcast.json', orient="records")
+    
+        # with open('forcast.json', 'r') as json_file:
+        #     json_load = json.load(json_file)
+        #     #url = "https://demo.bizgaze.app/apis/v4/bizgaze/integrations/demandforecast/saveforecast/List"
+        #     url='https://qa.bizgaze.app/apis/v4/bizgaze/integrations/demandforecast/saveforecast/List'
+    
+        # payload = json.dumps(json_load)#.replace("]", "").replace("[", "")
+        # print(payload)
+        # headers = {
+        #     #'Authorization': 'stat 263162e61f084d3392f162eb7ec39b2c',#demo
+        #     'Authorization': 'stat 873f2e6f70b3483e983972f96fbf5ea4',#test
+        #     'Content-Type': 'application/json'
+        # }
+        # response = requests.request("POST", url, headers=headers, data=payload)
+        # print("##############################################################")
+        # print(response.text)
+    
+    
+        # import time
+        # time.sleep(1)   
+
+
+
+###############################################################################################################################################################
+
+#####################################################################################################################
+
+@app.route("/sales_forcast", methods=["GET", "POST"])
+def sales_forcast():
+    #wise= request.args.get('wise').replace('{','').replace('}','')
+    #Num= request.args.get('value').replace('{','').replace('}','')
+    #print(wise)
+    #print(Num)
+    Dataset = request.get_json()
+    #print(Dataset)
+    import pandas as pd
+    df=pd.DataFrame(Dataset)
+    print(df)
+    # a = Dataset
+    #x = a['wise']
+    # cmd = "python C:\\Users\\Bizga\\Desktop\\forcast\\XGdaywise.py"
+    # os.system(cmd)
+   
+    #split=wise
+    wise='month'
+    Num=5
+    if wise=='days':
+        print('daywise groupby')
+        day(Num,df)
+        # cmd = "python C:\\Users\\Bizga\\Desktop\\forcast\\XGdaywise.py"+" "+ Num
+        # os.system(cmd)
+    else:
+        print('monthwise groupby')
+        output=month(Num,df)
+        payload = json.dumps(output)
+        payload_list="["+payload+"]"
+        #payload_list.append(payload)
+        # print(payload)
+
+        # cmd = "python C:\\Users\\Bizga\\Desktop\\forcast\\xgmonthwise.py"+" "+ Num
+        # os.system(cmd)
+    # import json
+    # a={"status":"success"}
+    # payload123 = json.dumps(a)
+    return output
+
+if __name__ == "__main__":
+    app.run(host='0.0.0.0', port=5003)