diff --git a/API/__pycache__/app.cpython-310.pyc b/API/__pycache__/app.cpython-310.pyc
index ed06d17969dd11b823a4e3e47489627a8cbf771a..e0cb02c71747bd6c7c0edfdb70161572f9f8e08a 100644
Binary files a/API/__pycache__/app.cpython-310.pyc and b/API/__pycache__/app.cpython-310.pyc differ
diff --git a/API/run.py b/API/run.py
index 8b37567de7b79ffcae908852f06862f03f6e0464..27caf22fe4b32836afcf53f4327528f1b7ebf032 100644
--- a/API/run.py
+++ b/API/run.py
@@ -1,3 +1,23 @@
+# import libraries
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from collections import Counter
+import statistics
+import math
+
+#for LSTM model
+from sklearn.preprocessing import MinMaxScaler
+from keras.models import Sequential
+from keras.layers import Dense, LSTM, Dropout
+
+# ignore warnings
+import warnings
+warnings.filterwarnings("ignore")
+
+from datetime import datetime as dt
+
import pymysql
import json
from app import app
@@ -22,322 +42,47 @@ plt.rcParams.update({'figure.figsize':(9,7), 'figure.dpi':120})
import pmdarima as pm
-app.config['SECRET_KEY']='a1b1'
-
-@app.route('/predict',methods=['POST'])
-def predict():
-
- data=request.get_json()
-
- return model1(data)
-
-def model1(income_data):
-
- X=[]
- Y=[]
-
- data_arr=json.dumps(income_data)
- din=json.loads(data_arr)
- for i in din:
- X.append(i)
- Y.append(din[i])
-
- data_time = np.asarray(X)
- data_count = np.asarray(Y)
-
- from sklearn.model_selection import train_test_split
- X_Train, X_Test, Y_Train, Y_Test = train_test_split(X, Y, test_size = 1/3, random_state = 0)
-
- df = pd.DataFrame({'time': data_time, 'count': data_count})
-
-
- df.time = pd.to_datetime(df.time)
-
- regr = linear_model.LinearRegression()
- regr.fit(df.time.values.reshape(-1, 1), df['count'].values.reshape(-1, 1))
-
- y_pred = regr.predict(df.time.values.astype(float).reshape(-1, 1))
- df['pred'] = y_pred
-
- print(df)
-
-
- df = df.set_index(data_time)
-
- out=df.to_json(orient='columns')
-
- y = json.loads(out)
-
- return jsonify(y['pred'])
-
-
-
-
-@app.route('/m1',methods=['POST'])
-def m1():
-
- data=request.get_json()
-
- return model1(data)
-
-def model1(income_data):
-
- X=[]
- Y=[]
-
- data_arr=json.dumps(income_data)
- din=json.loads(data_arr)
- for i in din:
- X.append(i)
- Y.append(din[i])
-
- data_time = np.asarray(X)
- data_count = np.asarray(Y)
-
-
-
- from sklearn.model_selection import train_test_split
- X_Train, X_Test, Y_Train, Y_Test = train_test_split(X, Y, test_size = 1/3, random_state = 0)
-
- df = pd.DataFrame({'time': data_time, 'count': data_count})
-
-
- df.time = pd.to_datetime(df.time)
-
- regr = linear_model.LinearRegression()
-
- regr.fit(df.time.values.reshape(-1, 1), df['count'].values.reshape(-1, 1))
-
- y_pred = regr.predict(df.time.values.astype(float).reshape(-1, 1))
- df['pre'] = y_pred
-
- print(df)
-
-
- df = df.set_index(data_time)
-
- out=df.to_json(orient='columns')
-
- y = json.loads(out)
-
- ax = plt.gca()
- df.plot(kind='line',x='time',y='count',color='blue',ax=ax)
-
- df.plot(kind='line',x='time',y='pre',color='red',ax=ax)
- plt.show()
-
- return jsonify(y['pre'])
-
-
-@app.route('/m2',methods=['POST'])
-def m2():
-
- data=request.get_json()
-
- return model2(data)
-
-def model2(income_data):
-
- X=[]
- Y=[]
-
- data_arr=json.dumps(income_data)
- din=json.loads(data_arr)
- for i in din:
- X.append(i)
- Y.append(din[i])
-
- data_time = np.asarray(X)
- data_count = np.asarray(Y)
-
-
- df = pd.DataFrame({'time': data_time, 'count': data_count})
- df.time = pd.to_datetime(df.time)
-
-
-
-
- model = LorentzianModel()
- params = model.guess(df['count'], x=df.time.values.astype(float))
- result = model.fit(df['count'], params, x=df.time.values.astype(float))
- result.plot_fit()
- plt.show()
-
-
- y = np.array(result.best_fit)
- df['pre'] =y
- df = df.set_index(data_time)
- print(result.fit_report())
- out=df.to_json(orient='columns')
-
- y = json.loads(out)
-
-
-
- return jsonify(y['pre'])
-
-
-
-
-@app.route('/p1',methods=['POST'])
-def p1():
-
- data=request.get_json()
-
- return model2(data)
-
-def model2(income_data):
-
- X=[]
- Y=[]
-
- data_arr=json.dumps(income_data)
- din=json.loads(data_arr)
- for i in din:
- X.append(i)
- Y.append(din[i])
-
-
-
- data_time = np.asarray(X)
- data_count = np.asarray(Y)
-
- data = pd.DataFrame({'date': data_time, 'value': data_count})
- data.date = pd.to_datetime(data.date)
- data.set_index(data_time)
-
-
- csv_data = data.to_csv('test2.csv', index=False)
- print(csv_data)
-
- data = pd.read_csv('test2.csv', parse_dates=['date'], index_col='date')
-
- # Seasonal - fit stepwise auto-ARIMA
- smodel = pm.auto_arima(data, start_p=1, start_q=1,
- test='adf',
- max_p=3, max_q=3, m=12,
- start_P=0, seasonal=True,
- d=None, D=1, trace=True,
- error_action='ignore',
- suppress_warnings=True,
- stepwise=True)
-
- smodel.summary()
-
- # Forecast
- n_periods =5
- fitted, confint = smodel.predict(n_periods=n_periods, return_conf_int=True)
- index_of_fc = pd.date_range(data.index[-1], periods = n_periods, freq='MS')
-
- # make series for plotting purpose
- fitted_series = pd.Series(fitted, index=index_of_fc)
- lower_series = pd.Series(confint[:, 0], index=index_of_fc)
- upper_series = pd.Series(confint[:, 1], index=index_of_fc)
-
-
-
- dy = fitted_series.to_frame()
-
-
-
-
- print(dy)
-
- out=dy.to_json(orient='index',date_format='iso')
-
- result = json.loads(out)
-
- print(out)
-
- return jsonify(result)
-
-
-
-
-@app.route('/p2',methods=['POST'])
-def p2():
-
- data=request.get_json()
-
- return model2(data)
-
-def model2(income_data):
+@app.route('/start',methods=['POST'])
- X=[]
- Y=[]
+def start():
- data_arr=json.dumps(income_data)
- din=json.loads(data_arr)
- for i in din:
- X.append(i)
- Y.append(din[i])
-
-
+ data=request.get_json()
- data_time = np.asarray(X)
- data_count = np.asarray(Y)
-
- data = pd.DataFrame({'date': data_time, 'value': data_count})
- data.date = pd.to_datetime(data.date)
- data.set_index(data_time)
-
- csv_data = data.to_csv('test2.csv', index=False)
- print(csv_data)
+ return data
- data = pd.read_csv('test2.csv', parse_dates=['date'], index_col='date')
- # Seasonal - fit stepwise auto-ARIMA
- smodel = pm.auto_arima(data, start_p=1, start_q=1,
- test='adf',
- max_p=3, max_q=3, m=12,
- start_P=0, seasonal=True,
- d=None, D=1, trace=True,
- error_action='ignore',
- suppress_warnings=True,
- stepwise=True)
+def read_json(income_data):
- smodel.summary()
+ X=[]
+ Y=[]
- # Forecast
- n_periods =5
- fitted, confint = smodel.predict(n_periods=n_periods, return_conf_int=True)
- index_of_fc = pd.date_range(data.index[-1], periods = n_periods, freq='MS')
+ data_arr=json.dumps(income_data)
+ din=json.loads(data_arr)
+ for i in din:
+ X.append(i)
+ Y.append(din[i])
+
+ data_time = np.asarray(X)
+ data_count = np.asarray(Y)
- # make series for plotting purpose
- fitted_series = pd.Series(fitted, index=index_of_fc)
- lower_series = pd.Series(confint[:, 0], index=index_of_fc)
- upper_series = pd.Series(confint[:, 1], index=index_of_fc)
-
-
-
- # Plot
- plt.plot(data)
- plt.plot(fitted_series, color='darkgreen')
- plt.fill_between(lower_series.index,
- lower_series,
- upper_series,
- color='k', alpha=.15)
+ return "json"
- plt.title("Final Forecast")
- plt.show()
+@app.route('/tranning',methods=['POST'])
- dy = fitted_series.to_frame()
-
-
-
-
- print(dy)
+def tranning():
+ return "tranning"
- out=dy.to_json(orient='index',date_format='iso')
- result = json.loads(out)
+@app.route('/prediction',methods=['POST'])
- print(out)
-
- return jsonify(result)
+def prediction():
+ return "prediction"
+@app.route('/optimize',methods=['POST'])
+def optimize():
+ return "optimize"
if __name__ == "__main__":
app.run()
\ No newline at end of file
diff --git a/API/.idea/Prediction_api.iml b/API_bk/.idea/Prediction_api.iml
similarity index 100%
rename from API/.idea/Prediction_api.iml
rename to API_bk/.idea/Prediction_api.iml
diff --git a/API/.idea/inspectionProfiles/profiles_settings.xml b/API_bk/.idea/inspectionProfiles/profiles_settings.xml
similarity index 100%
rename from API/.idea/inspectionProfiles/profiles_settings.xml
rename to API_bk/.idea/inspectionProfiles/profiles_settings.xml
diff --git a/API/.idea/misc.xml b/API_bk/.idea/misc.xml
similarity index 100%
rename from API/.idea/misc.xml
rename to API_bk/.idea/misc.xml
diff --git a/API/.idea/modules.xml b/API_bk/.idea/modules.xml
similarity index 100%
rename from API/.idea/modules.xml
rename to API_bk/.idea/modules.xml
diff --git a/API/.idea/workspace.xml b/API_bk/.idea/workspace.xml
similarity index 100%
rename from API/.idea/workspace.xml
rename to API_bk/.idea/workspace.xml
diff --git a/API/1D_json.txt b/API_bk/1D_json.txt
similarity index 100%
rename from API/1D_json.txt
rename to API_bk/1D_json.txt
diff --git a/API/JwtApi.py b/API_bk/JwtApi.py
similarity index 100%
rename from API/JwtApi.py
rename to API_bk/JwtApi.py
diff --git a/API/JwtApi.wsgi b/API_bk/JwtApi.wsgi
similarity index 100%
rename from API/JwtApi.wsgi
rename to API_bk/JwtApi.wsgi
diff --git a/API/__init__.py b/API_bk/__init__.py
similarity index 100%
rename from API/__init__.py
rename to API_bk/__init__.py
diff --git a/API_bk/__pycache__/app.cpython-310.pyc b/API_bk/__pycache__/app.cpython-310.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..ed06d17969dd11b823a4e3e47489627a8cbf771a
Binary files /dev/null and b/API_bk/__pycache__/app.cpython-310.pyc differ
diff --git a/API/__pycache__/app.cpython-36.pyc b/API_bk/__pycache__/app.cpython-36.pyc
similarity index 100%
rename from API/__pycache__/app.cpython-36.pyc
rename to API_bk/__pycache__/app.cpython-36.pyc
diff --git a/API/__pycache__/app.cpython-38.pyc b/API_bk/__pycache__/app.cpython-38.pyc
similarity index 100%
rename from API/__pycache__/app.cpython-38.pyc
rename to API_bk/__pycache__/app.cpython-38.pyc
diff --git a/API/__pycache__/db_config.cpython-310.pyc b/API_bk/__pycache__/db_config.cpython-310.pyc
similarity index 100%
rename from API/__pycache__/db_config.cpython-310.pyc
rename to API_bk/__pycache__/db_config.cpython-310.pyc
diff --git a/API/__pycache__/db_config.cpython-36.pyc b/API_bk/__pycache__/db_config.cpython-36.pyc
similarity index 100%
rename from API/__pycache__/db_config.cpython-36.pyc
rename to API_bk/__pycache__/db_config.cpython-36.pyc
diff --git a/API/__pycache__/db_config.cpython-38.pyc b/API_bk/__pycache__/db_config.cpython-38.pyc
similarity index 100%
rename from API/__pycache__/db_config.cpython-38.pyc
rename to API_bk/__pycache__/db_config.cpython-38.pyc
diff --git a/API/__pycache__/run.cpython-310.pyc b/API_bk/__pycache__/run.cpython-310.pyc
similarity index 100%
rename from API/__pycache__/run.cpython-310.pyc
rename to API_bk/__pycache__/run.cpython-310.pyc
diff --git a/API/__pycache__/run.cpython-38.pyc b/API_bk/__pycache__/run.cpython-38.pyc
similarity index 100%
rename from API/__pycache__/run.cpython-38.pyc
rename to API_bk/__pycache__/run.cpython-38.pyc
diff --git a/API/__pycache__/views.cpython-310.pyc b/API_bk/__pycache__/views.cpython-310.pyc
similarity index 100%
rename from API/__pycache__/views.cpython-310.pyc
rename to API_bk/__pycache__/views.cpython-310.pyc
diff --git a/API/__pycache__/views.cpython-38.pyc b/API_bk/__pycache__/views.cpython-38.pyc
similarity index 100%
rename from API/__pycache__/views.cpython-38.pyc
rename to API_bk/__pycache__/views.cpython-38.pyc
diff --git a/API/api.py b/API_bk/api.py
similarity index 100%
rename from API/api.py
rename to API_bk/api.py
diff --git a/API_bk/app.py b/API_bk/app.py
new file mode 100644
index 0000000000000000000000000000000000000000..7232d4ace11b3923eb78839920e3e65ba7823774
--- /dev/null
+++ b/API_bk/app.py
@@ -0,0 +1,3 @@
+from flask import Flask
+
+app = Flask(__name__)
\ No newline at end of file
diff --git a/API/app.pyc b/API_bk/app.pyc
similarity index 100%
rename from API/app.pyc
rename to API_bk/app.pyc
diff --git a/API/back.py b/API_bk/back.py
similarity index 100%
rename from API/back.py
rename to API_bk/back.py
diff --git a/API/best_fit.py b/API_bk/best_fit.py
similarity index 100%
rename from API/best_fit.py
rename to API_bk/best_fit.py
diff --git a/API/dae.csv b/API_bk/dae.csv
similarity index 100%
rename from API/dae.csv
rename to API_bk/dae.csv
diff --git a/API/data.csv b/API_bk/data.csv
similarity index 100%
rename from API/data.csv
rename to API_bk/data.csv
diff --git a/API/data.xlsx b/API_bk/data.xlsx
similarity index 100%
rename from API/data.xlsx
rename to API_bk/data.xlsx
diff --git a/API/db_config.py b/API_bk/db_config.py
similarity index 100%
rename from API/db_config.py
rename to API_bk/db_config.py
diff --git a/API/db_config.pyc b/API_bk/db_config.pyc
similarity index 100%
rename from API/db_config.pyc
rename to API_bk/db_config.pyc
diff --git a/API/json.txt b/API_bk/json.txt
similarity index 100%
rename from API/json.txt
rename to API_bk/json.txt
diff --git a/API/models.py b/API_bk/models.py
similarity index 100%
rename from API/models.py
rename to API_bk/models.py
diff --git a/API/p2.py b/API_bk/p2.py
similarity index 100%
rename from API/p2.py
rename to API_bk/p2.py
diff --git a/API/p3.py b/API_bk/p3.py
similarity index 100%
rename from API/p3.py
rename to API_bk/p3.py
diff --git a/API/p4.py b/API_bk/p4.py
similarity index 100%
rename from API/p4.py
rename to API_bk/p4.py
diff --git a/API/resources.py b/API_bk/resources.py
similarity index 100%
rename from API/resources.py
rename to API_bk/resources.py
diff --git a/API/run._oopy b/API_bk/run._oopy
similarity index 100%
rename from API/run._oopy
rename to API_bk/run._oopy
diff --git a/API_bk/run.py b/API_bk/run.py
new file mode 100644
index 0000000000000000000000000000000000000000..8b37567de7b79ffcae908852f06862f03f6e0464
--- /dev/null
+++ b/API_bk/run.py
@@ -0,0 +1,343 @@
+import pymysql
+import json
+from app import app
+
+from flask import Flask, jsonify, request, make_response
+from flask import flash, request
+
+import datetime
+from werkzeug.security import generate_password_hash, check_password_hash
+from functools import wraps
+import requests
+import numpy as np
+import pandas as pd
+from sklearn import linear_model
+from datetime import datetime, timedelta
+
+from statsmodels.tsa.ar_model import AR
+
+from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
+import matplotlib.pyplot as plt
+plt.rcParams.update({'figure.figsize':(9,7), 'figure.dpi':120})
+import pmdarima as pm
+
+
+app.config['SECRET_KEY']='a1b1'
+
+@app.route('/predict',methods=['POST'])
+def predict():
+
+ data=request.get_json()
+
+ return model1(data)
+
+def model1(income_data):
+
+ X=[]
+ Y=[]
+
+ data_arr=json.dumps(income_data)
+ din=json.loads(data_arr)
+ for i in din:
+ X.append(i)
+ Y.append(din[i])
+
+ data_time = np.asarray(X)
+ data_count = np.asarray(Y)
+
+ from sklearn.model_selection import train_test_split
+ X_Train, X_Test, Y_Train, Y_Test = train_test_split(X, Y, test_size = 1/3, random_state = 0)
+
+ df = pd.DataFrame({'time': data_time, 'count': data_count})
+
+
+ df.time = pd.to_datetime(df.time)
+
+ regr = linear_model.LinearRegression()
+ regr.fit(df.time.values.reshape(-1, 1), df['count'].values.reshape(-1, 1))
+
+ y_pred = regr.predict(df.time.values.astype(float).reshape(-1, 1))
+ df['pred'] = y_pred
+
+ print(df)
+
+
+ df = df.set_index(data_time)
+
+ out=df.to_json(orient='columns')
+
+ y = json.loads(out)
+
+ return jsonify(y['pred'])
+
+
+
+
+@app.route('/m1',methods=['POST'])
+def m1():
+
+ data=request.get_json()
+
+ return model1(data)
+
+def model1(income_data):
+
+ X=[]
+ Y=[]
+
+ data_arr=json.dumps(income_data)
+ din=json.loads(data_arr)
+ for i in din:
+ X.append(i)
+ Y.append(din[i])
+
+ data_time = np.asarray(X)
+ data_count = np.asarray(Y)
+
+
+
+ from sklearn.model_selection import train_test_split
+ X_Train, X_Test, Y_Train, Y_Test = train_test_split(X, Y, test_size = 1/3, random_state = 0)
+
+ df = pd.DataFrame({'time': data_time, 'count': data_count})
+
+
+ df.time = pd.to_datetime(df.time)
+
+ regr = linear_model.LinearRegression()
+
+ regr.fit(df.time.values.reshape(-1, 1), df['count'].values.reshape(-1, 1))
+
+ y_pred = regr.predict(df.time.values.astype(float).reshape(-1, 1))
+ df['pre'] = y_pred
+
+ print(df)
+
+
+ df = df.set_index(data_time)
+
+ out=df.to_json(orient='columns')
+
+ y = json.loads(out)
+
+ ax = plt.gca()
+ df.plot(kind='line',x='time',y='count',color='blue',ax=ax)
+
+ df.plot(kind='line',x='time',y='pre',color='red',ax=ax)
+ plt.show()
+
+ return jsonify(y['pre'])
+
+
+@app.route('/m2',methods=['POST'])
+def m2():
+
+ data=request.get_json()
+
+ return model2(data)
+
+def model2(income_data):
+
+ X=[]
+ Y=[]
+
+ data_arr=json.dumps(income_data)
+ din=json.loads(data_arr)
+ for i in din:
+ X.append(i)
+ Y.append(din[i])
+
+ data_time = np.asarray(X)
+ data_count = np.asarray(Y)
+
+
+ df = pd.DataFrame({'time': data_time, 'count': data_count})
+ df.time = pd.to_datetime(df.time)
+
+
+
+
+ model = LorentzianModel()
+ params = model.guess(df['count'], x=df.time.values.astype(float))
+ result = model.fit(df['count'], params, x=df.time.values.astype(float))
+ result.plot_fit()
+ plt.show()
+
+
+ y = np.array(result.best_fit)
+ df['pre'] =y
+ df = df.set_index(data_time)
+ print(result.fit_report())
+ out=df.to_json(orient='columns')
+
+ y = json.loads(out)
+
+
+
+ return jsonify(y['pre'])
+
+
+
+
+@app.route('/p1',methods=['POST'])
+def p1():
+
+ data=request.get_json()
+
+ return model2(data)
+
+def model2(income_data):
+
+ X=[]
+ Y=[]
+
+ data_arr=json.dumps(income_data)
+ din=json.loads(data_arr)
+ for i in din:
+ X.append(i)
+ Y.append(din[i])
+
+
+
+ data_time = np.asarray(X)
+ data_count = np.asarray(Y)
+
+ data = pd.DataFrame({'date': data_time, 'value': data_count})
+ data.date = pd.to_datetime(data.date)
+ data.set_index(data_time)
+
+
+ csv_data = data.to_csv('test2.csv', index=False)
+ print(csv_data)
+
+ data = pd.read_csv('test2.csv', parse_dates=['date'], index_col='date')
+
+ # Seasonal - fit stepwise auto-ARIMA
+ smodel = pm.auto_arima(data, start_p=1, start_q=1,
+ test='adf',
+ max_p=3, max_q=3, m=12,
+ start_P=0, seasonal=True,
+ d=None, D=1, trace=True,
+ error_action='ignore',
+ suppress_warnings=True,
+ stepwise=True)
+
+ smodel.summary()
+
+ # Forecast
+ n_periods =5
+ fitted, confint = smodel.predict(n_periods=n_periods, return_conf_int=True)
+ index_of_fc = pd.date_range(data.index[-1], periods = n_periods, freq='MS')
+
+ # make series for plotting purpose
+ fitted_series = pd.Series(fitted, index=index_of_fc)
+ lower_series = pd.Series(confint[:, 0], index=index_of_fc)
+ upper_series = pd.Series(confint[:, 1], index=index_of_fc)
+
+
+
+ dy = fitted_series.to_frame()
+
+
+
+
+ print(dy)
+
+ out=dy.to_json(orient='index',date_format='iso')
+
+ result = json.loads(out)
+
+ print(out)
+
+ return jsonify(result)
+
+
+
+
+@app.route('/p2',methods=['POST'])
+def p2():
+
+ data=request.get_json()
+
+ return model2(data)
+
+def model2(income_data):
+
+ X=[]
+ Y=[]
+
+ data_arr=json.dumps(income_data)
+ din=json.loads(data_arr)
+ for i in din:
+ X.append(i)
+ Y.append(din[i])
+
+
+
+ data_time = np.asarray(X)
+ data_count = np.asarray(Y)
+
+ data = pd.DataFrame({'date': data_time, 'value': data_count})
+ data.date = pd.to_datetime(data.date)
+ data.set_index(data_time)
+
+
+ csv_data = data.to_csv('test2.csv', index=False)
+ print(csv_data)
+
+ data = pd.read_csv('test2.csv', parse_dates=['date'], index_col='date')
+
+ # Seasonal - fit stepwise auto-ARIMA
+ smodel = pm.auto_arima(data, start_p=1, start_q=1,
+ test='adf',
+ max_p=3, max_q=3, m=12,
+ start_P=0, seasonal=True,
+ d=None, D=1, trace=True,
+ error_action='ignore',
+ suppress_warnings=True,
+ stepwise=True)
+
+ smodel.summary()
+
+ # Forecast
+ n_periods =5
+ fitted, confint = smodel.predict(n_periods=n_periods, return_conf_int=True)
+ index_of_fc = pd.date_range(data.index[-1], periods = n_periods, freq='MS')
+
+ # make series for plotting purpose
+ fitted_series = pd.Series(fitted, index=index_of_fc)
+ lower_series = pd.Series(confint[:, 0], index=index_of_fc)
+ upper_series = pd.Series(confint[:, 1], index=index_of_fc)
+
+
+
+ # Plot
+ plt.plot(data)
+ plt.plot(fitted_series, color='darkgreen')
+ plt.fill_between(lower_series.index,
+ lower_series,
+ upper_series,
+ color='k', alpha=.15)
+
+ plt.title("Final Forecast")
+ plt.show()
+
+ dy = fitted_series.to_frame()
+
+
+
+
+ print(dy)
+
+ out=dy.to_json(orient='index',date_format='iso')
+
+ result = json.loads(out)
+
+ print(out)
+
+ return jsonify(result)
+
+
+
+if __name__ == "__main__":
+ app.run()
\ No newline at end of file
diff --git a/API/run_bk.py b/API_bk/run_bk.py
similarity index 100%
rename from API/run_bk.py
rename to API_bk/run_bk.py
diff --git a/API/sample.csv b/API_bk/sample.csv
similarity index 100%
rename from API/sample.csv
rename to API_bk/sample.csv
diff --git a/API/stock.py b/API_bk/stock.py
similarity index 100%
rename from API/stock.py
rename to API_bk/stock.py
diff --git a/API/stock_data.csv b/API_bk/stock_data.csv
similarity index 100%
rename from API/stock_data.csv
rename to API_bk/stock_data.csv
diff --git a/API/test2.csv b/API_bk/test2.csv
similarity index 100%
rename from API/test2.csv
rename to API_bk/test2.csv
diff --git a/API/test_time.py b/API_bk/test_time.py
similarity index 100%
rename from API/test_time.py
rename to API_bk/test_time.py
diff --git a/API/views.py b/API_bk/views.py
similarity index 100%
rename from API/views.py
rename to API_bk/views.py