def Randomforestregressor(self, n_estimators):
rf = RandomForestRegressor(n_estimators)
rf.fit(self.x_train, self.y_train)
pred = rf.predict(self.x_test)
pred = pd.DataFrame(pred)
predictions = pd.merge(self.x_test, pred, left_index=True, right_index=True, how='inner')
predictions['num_orders'] = predictions[0]
predictions = predictions.drop([0], axis=1)
ts_tot_pred = predictions.groupby(['week'])['num_orders'].sum()
ts_tot_pred = pd.DataFrame(ts_tot_pred)
fig = Figure(figsize=(5, 5), dpi=100)
fig.add_subplot(111).plot(self.ts_tot_orders, color= 'Blue')
fig.add_subplot(111).plot(ts_tot_pred, color= 'Red')
ideaLib.py2idea(dataframe= ts_tot_pred,
databaseName= 'ts_tot_pred_rf',
client= client)
if self.is_canvas_ml == 1:
self.canvas.get_tk_widget().pack_forget()
self.canvas = FigureCanvasTkAgg(fig, master =self.ml) # A tk.DrawingArea.
self.canvas.get_tk_widget().pack(side=RIGHT)
self.canvas.draw()
self.is_canvas_ml = 1
def load_test(self):
self.filename = filedialog.askopenfilename(initialdir="/",
title="Select a File",
filetypes=(("Excel files", ".IMD*"), ("all files",
"*.*"),
("Excel files", ".csv*")))
self.datatype = self.filename.split('.')
if (self.datatype[-1] == 'csv'):
self.test = pd.read_csv(self.filename)
elif self.datatype[-1] == 'IMD':
# Read from .IMD file
self.filename=self.filename.split('/')
self.filename=self.filename[-1] # Dataset must be in IDEA working directory
self.test = ideaLib.idea2py(database = self.filename)
if self.test is None:
messagebox.showinfo("Info",
"There was something wrong with the import process of IDEA database to Pandas dataframe")
elif self.test.empty:
messagebox.showinfo("Info","You selected an empty IDEA database")
if self.datatype[-1] == 'IMD' or 'csv':
self.test.columns = map(str.lower, self.test.columns)
self.x_test = self.test.copy()
else :
messagebox.showerror('Error', 'Invalid Data Type')
def load(self):
self.lbdata.delete(0, 'end')
self.filename = filedialog.askopenfilename(
initialdir="/",
title="Select a File",
filetypes=(("Excel files", ".IMD*"), ("all files", "*.*"),
("Excel files", ".csv*")))
self.datatype = self.filename.split('.')
if (self.datatype[-1] == 'csv'):
self.df = pd.read_csv(self.filename)
# self.indexedDataset= self.df.groupby(['date'])['num_orders'].sum().reset_index()
# self.indexedDataset.set_index(['date'],inplace=True)
elif self.datatype[-1] == 'IMD':
self.datalocation['text'] = self.filename
# Read from .IMD file
self.filename = self.filename.split('/')
self.filename = self.filename[
-1] # Dataset must be in IDEA working directory
self.df = ideaLib.idea2py(database=self.filename)
if self.df is None:
messagebox.showinfo(
"Info",
"There was something wrong with the import process of IDEA database to Pandas dataframe"
)
elif self.df.empty:
messagebox.showinfo("Info", "You selected an empty IDEA database")
if self.datatype[-1] == 'IMD':
if 'CENTER_TYPE' in self.df and \
'CATEGORY' in self.df and \
'CUISINE' in self.df:
self.df = self.df.astype({
"CENTER_TYPE": str,
"CATEGORY": str,
"CUISINE": str
})
self.df.columns = map(str.lower, self.df.columns)
# self.indexedDataset= self.df.groupby(['date'])['num_orders'].sum().reset_index()
# self.indexedDataset.set_index(['date'],inplace=True)
i = 0
for column in self.df.columns:
self.lbdata.insert(i, column)
i += 1
elif self.datatype[-1] == 'csv':
self.df.columns = map(str.lower, self.df.columns)
i = 0
for column in self.df.columns:
self.lbdata.insert(i, column)
i += 1
else:
messagebox.showerror('Error', 'Invalid Data Type')
def load_train(self):
self.filename = filedialog.askopenfilename(
initialdir="/",
title="Select a File",
filetypes=(("Excel files", ".IMD*"), ("all files", "*.*"),
("Excel files", ".csv*")))
self.datatype = self.filename.split('.')
if (self.datatype[-1] == 'csv'):
self.train = pd.read_csv(self.filename)
elif self.datatype[-1] == 'IMD':
# Read from .IMD file
self.filename = self.filename.split('/')
self.filename = self.filename[
-1] # Dataset must be in IDEA working directory
self.train = ideaLib.idea2py(database=self.filename)
if self.train is None:
messagebox.showinfo(
"Info", "There was something wrong with the import \
process of IDEA database to Pandas dataframe")
elif self.train.empty:
messagebox.showinfo("Info", "You selected an empty IDEA database")
# pd.set_option('display.max_columns', None)
# pd.set_option("display.float_format",lambda x:"%.4f" % x)
if self.datatype[-1] == 'csv' or 'IMD':
self.train.columns = map(str.lower, self.train.columns)
if "week" in self.train:
self.ts_tot_orders = self.train.groupby(
['week'])['num_orders'].sum()
else:
self.ts_tot_orders = self.train.groupby(
['date'])['sales'].sum().reset_index()
self.ts_tot_orders['date'] = pd.to_datetime(
self.ts_tot_orders['date'])
# self.ts_tot_orders['date']=self.ts_tot_orders['date'].map(dt.datetime.toordinal)
self.ts_tot_orders = self.ts_tot_orders.set_index(['date'])
self.ts_tot_orders = self.ts_tot_orders.iloc[:, -1]
self.y_train = self.train.iloc[:, -1]
self.x_train = self.train.iloc[:, 0:-1]
if 'id' in self.x_train:
self.x_train = self.x_train.drop(['id'], axis=1)
if 'date' in self.x_train:
self.x_train['date'] = pd.to_datetime(self.x_train['date'])
# self.x_train['date']=self.x_train['date'].map(dt.datetime.toordinal)
self.x_train = self.x_train.set_index(['date'])
else:
messagebox.showerror('Error', 'Invalid Data Type')
def Linearregression(self):
lr = LinearRegression()
lr.fit(self.x_train, self.y_train)
pred = lr.predict(self.x_test)
pred = pd.DataFrame(pred)
# predictions = pd.merge(self.x_test, pred, left_index=True,
# right_index=True, how='inner')
x_test = self.x_test.reset_index()
predictions = pd.concat([x_test, pred], axis=1)
predictions['num_orders'] = predictions[0]
predictions = predictions.drop([0], axis=1)
print("predictions\n", predictions)
if 'week' in predictions:
ts_tot_pred = predictions.groupby(['week'])['num_orders'].sum()
ts_tot_pred = pd.DataFrame(ts_tot_pred)
else:
ts_tot_pred = pd.DataFrame(predictions)
ts_tot_pred = predictions.groupby(['date'])['num_orders'].sum()
print("ts_tot_pred\n", ts_tot_pred)
fig = Figure(figsize=(5, 5), dpi=100)
fig.add_subplot(111).plot(self.ts_tot_orders, color='Blue')
fig.add_subplot(111).plot(ts_tot_pred, color='Red')
ideaLib.py2idea(dataframe=ts_tot_pred,
databaseName='ts_tot_pred_linear',
client=client)
if self.is_canvas_ml == 1:
self.canvas.get_tk_widget().pack_forget()
self.canvas = FigureCanvasTkAgg(fig,
master=self.ml) # A tk.DrawingArea.
self.canvas.get_tk_widget().pack(side=RIGHT)
self.canvas.draw()
self.is_canvas_ml = 1
def Decisiontreeregressor(self):
dt = DecisionTreeRegressor()
dt.fit(self.x_train, self.y_train)
pred = dt.predict(self.x_test)
pred = pd.DataFrame(pred)
x_test = self.x_test.reset_index()
predictions = pd.concat([x_test, pred], axis=1)
predictions['num_orders'] = predictions[0]
predictions = predictions.drop([0], axis=1)
print("predictions\n", predictions)
if 'week' in predictions:
ts_tot_pred = predictions.groupby(['week'])['num_orders'].sum()
ts_tot_pred = pd.DataFrame(ts_tot_pred)
else:
ts_tot_pred = pd.DataFrame(predictions)
ts_tot_pred = predictions.groupby(['date'])['num_orders'].sum()
print("ts_tot_pred\n", ts_tot_pred)
if self.is_canvas_ml == 1:
self.canvas.get_tk_widget().pack_forget()
fig = Figure(figsize=(5, 5), dpi=100)
fig.add_subplot(111).plot(self.ts_tot_orders, color='Blue')
fig.add_subplot(111).plot(ts_tot_pred, color='Red')
ideaLib.py2idea(dataframe=ts_tot_pred,
databaseName='ts_tot_pred_dt',
client=client)
self.canvas = FigureCanvasTkAgg(fig,
master=self.ml) # A tk.DrawingArea.
self.canvas.get_tk_widget().pack(side=RIGHT)
self.canvas.draw()
self.is_canvas_ml = 1
def load(self):
self.filename = filedialog.askopenfilename(
initialdir="/",
title="Select a File",
filetypes=(("Excel files", ".IMD*"), ("all files", "*.*"),
("Excel files", ".csv*")))
self.datatype = self.filename.split('.')
if (self.datatype[-1] == 'csv'):
messagebox.showinfo('Info', 'Please try again later')
# self.df = pd.read_csv(self.filename)
# self.df = client.OpenDatabase(self.df)
elif self.datatype[-1] == 'IMD':
self.datalocation['text'] = self.filename
# Read from .IMD file
self.filename = self.filename.split('/')
self.filename = self.filename[
-1] # Dataset must be in IDEA working directory
self.df = ideaLib.idea2py(database=self.filename)
if self.df is None:
messagebox.showinfo(
"Info",
"There was something wrong with the import process of IDEA database to Pandas dataframe"
)
elif self.df.empty:
messagebox.showinfo("Info", "You selected an empty IDEA database")
if self.datatype[-1] == 'IMD':
# pd.set_option('display.max_columns', None)
# pd.set_option("display.float_format",lambda x:"%.4f" % x)
self.df = self.df.astype({
"CENTER_TYPE": str,
"CATEGORY": str,
"CUISINE": str
})
self.df.columns = map(str.lower, self.df.columns)
elif self.datatype[-1] == 'csv':
self.df.columns = map(str.lower, self.df.columns)
else:
messagebox.showerror('Error', 'Invalid Data Type')