def root():
# global model
global ridge
form = HouseForms(csrf_enabled=False)
return render_template("index1.html",
title="House Price Prediction",
form=form)
def root():
global model
form = HouseForms(csrf_enabled=False)
return render_template("index1.html",
title="House Price Prediction",
form=form,
prediction="Awaiting You")
def index():
# global model
global ridge
form = HouseForms(csrf_enabled=False)
# if (request.method == "POST") and (form.validate()):
user_dictionary = {
'zip': [str(int(form.zipcode.data))],
'type': [str(form.buildingType.data)],
'beds': [float(form.bedrooms.data)],
'baths': [float(form.bathrooms.data)],
'sqrft': [float(form.Squarefeet.data)],
'lot': [float(form.lotsize.data)],
'$/sqrft': [float(form.per_sqrft.data)]
}
user_df = pd.DataFrame(user_dictionary)
user_df_fit = pd.get_dummies(user_df, columns=['zip', 'type'])
n = train_flask()
for i in n.columns:
if i in user_df_fit.columns:
pass
else:
user_df_fit[i] = 0
print(user_df_fit)
# user_df_fit=user_df_fit.set_index('beds')
# prediction = np.expm1(model.predict(user_df_fit))
prediction = int(np.expm1(ridge.predict(user_df_fit)))
# prediction=ridge.predict(user_df_fit)
# prediction=model.predict(user_df_fit)
# p = round(prediction[0],2)
print([str(int(form.zipcode.data))])
print([str(form.buildingType.data)])
print([float(form.bedrooms.data)])
print([float(form.bathrooms.data)])
print([float(form.Squarefeet.data)])
print([float(form.lotsize.data)])
print([float(form.per_sqrft.data)])
print(n.head())
print(prediction)
# else:
# prediction = "N/A"
# print("what")
return render_template("index1.html",
title="House Price Prediction",
form=form,
prediction='${:,.2f}'.format(prediction))
def root():
# if city_entered=="Irvine" or city_entered=="irvine":
# global irvine_ridge
# else city_entered=="Tustin" or city_entered="tustin":
# global tustin_ridge
form = HouseForms(csrf_enabled=False)
return render_template("index1.html",
title="House Price Prediction",
form=form)
def index():
global model
form = HouseForms(csrf_enabled=False)
# if (request.method == "POST") and (form.validate()):
test_case = pd.DataFrame.from_dict({
"Overall Quality": [float(form.overallQuality.data)],
"Squarefeet": [float(form.area.data)],
"Bedrooms": [float(form.bedrooms.data)],
"Full Baths": [float(form.bathrooms.data)],
"Garage Cars": [float(form.garage.data)],
"Year Built": [float(form.yearBuilt.data)],
})
dummylist = []
dummylist = 15 * [0]
dummy_df = pd.DataFrame([dummylist])
test_case[[
"BldgType_1Fam", 'BldgType_2fmCon', 'BldgType_Duplex',
'BldgType_Twnhs', 'BldgType_TwnhsE', 'CentralAir_N', 'CentralAir_Y',
'HouseStyle_1.5Fin', 'HouseStyle_1.5Unf', 'HouseStyle_1Story',
'HouseStyle_2.5Fin', 'HouseStyle_2.5Unf', 'HouseStyle_2Story',
'HouseStyle_SFoyer', 'HouseStyle_SLvl'
]] = dummy_df
test_case.loc[0, form.buildingType.data] = 1
test_case.loc[0, form.houseStyle.data] = 1
test_case.loc[0, form.centralAir.data] = 1
prediction = model.predict(test_case)
p = round(prediction[0], 2)
print(p)
# else:
# prediction = "N/A"
# print("what")
return render_template("index1.html",
title="House Price Prediction",
form=form,
prediction=p)
def index():
# global irvine_ridge
form = HouseForms(csrf_enabled=False)
# city=[str(form.city.data)]
city = str(form.city.data)
year_entered = int(form.yearBuilt.data)
print(city)
print('hello')
n = train_flask()
minimums = min_built()
city_min = 0
bin_sample = 0
if city == "Irvine" or city == "irvine":
city_min = minimums[0]
bin_sample = n[0]['train_built'].unique()
# ['train_built']
if city == "tustin" or city == 'Tustin':
city_min = minimums[1]
bin_sample = n[2]['train_built'].unique()
if city == "Costa Mesa" or "Costa mesa" or "costa mesa":
city_min = minimums[2]
bin_sample = n[4]['train_built'].unique()
# if city=="Lake Forest" or "Lake forest" or "lake forest":
# city_min=minimums[3]
# bin_sample=n[6]['train_built'].unique()
print(minimums)
print(city_min)
print(bin_sample)
binned_yr = round((year_entered - city_min) / 10, 0)
#closest existing bin to binned_yr
def my_min(sequence):
low = sequence[0] # need to start with some value
for i in sequence:
if i < low:
low = i
return low
diff = []
for i in bin_sample:
x = abs(i - binned_yr)
diff.append(x)
min_difference = my_min(diff)
bin_index = diff.index(min_difference)
right_bin = bin_sample[bin_index]
print(type(right_bin))
user_dictionary = {
'zip': [str(int(form.zipcode.data))],
'train_built': [str(right_bin)],
'type': [str(form.buildingType.data)],
'beds': [float(form.bedrooms.data)],
'baths': [float(form.bathrooms.data)],
'sqrft': [float(form.Squarefeet.data)],
'lot': [float(form.lotsize.data)]
}
# 'city':[city]}
# [str(form.city.data)]}
print(f'user dictionariy: {user_dictionary}')
# 'train_built':[str(form.yearBuilt.data)]
user_df = pd.DataFrame(user_dictionary)
user_df_fit = pd.get_dummies(user_df,
columns=['zip', 'type', 'train_built'])
# n=train_flask()
# prediction=0
if city == "irvine" or city == "Irvine":
for i in n[1].columns:
if i in user_df_fit.columns:
pass
else:
user_df_fit[i] = 0
prediction = int(np.expm1(irvine_ridge.predict(user_df_fit)))
if city == "tustin" or city == "Tustin":
for i in n[3].columns:
if i in user_df_fit.columns:
pass
else:
user_df_fit[i] = 0
prediction = int(np.expm1(tustin_ridge.predict(user_df_fit)))
if city == "Costa mesa" or city == "Costa Mesa" or city == "costa mesa":
for i in n[5].columns:
if i in user_df_fit.columns:
pass
else:
user_df_fit[i] = 0
prediction = int(np.expm1(costamesa_ridge.predict(user_df_fit)))
# if city=="Lake Forest" or city=="Lake forest" or city=="lake forest":
# for i in n[7].columns:
# if i in user_df_fit.columns:
# pass
# else:
# user_df_fit[i]=0
# prediction = int(np.expm1(lakeforest_ridge.predict(user_df_fit)))
print(user_df_fit)
print(user_df_fit.columns)
print(n[1].columns)
# print(prediction)
# prediction = int(np.expm1(tustin_ridge.predict(user_df_fit)))
# prediction = int(np.expm1(tustin_ridge.predict(user_df_fit)))
# print([str(int(form.zipcode.data))])
# print([str(binned_yr)])
# print([str(form.buildingType.data)])
# print([float(form.bedrooms.data)])
# print([float(form.bathrooms.data)])
# print([float(form.Squarefeet.data)])
# print([float(form.lotsize.data)])
# print(n)
# print(prediction)
return render_template("index1.html",
title="House Price Prediction",
form=form,
prediction='${:,.2f}'.format(prediction))
def index():
global model
form = HouseForms(csrf_enabled=False)
overallquality = []
garagecars = []
area = []
fullbaths = []
yearbuilt = []
bedrooms = []
buildingtype = ""
centralair = ""
housestyle = ""
overallquality.append(form.overallQuality.data)
garagecars.append(form.garage.data)
area.append(form.area.data)
fullbaths.append(form.bathrooms.data)
yearbuilt.append(form.yearBuilt.data)
bedrooms.append(form.bedrooms.data)
buildingtype = form.buildingType.data
centralair = form.centralAir.data
housestyle = form.houseStyle.data
# print(model)
# test_case = pd.DataFrame.from_dict({
# "Overall Quality": [form.overallQuality.data],
# "Squarefeet": [form.area.data],
# "Bedrooms":[form.bedrooms.data],
# "Full Baths":[form.bathrooms.data],
# "Garage Cars":[form.garage.data],
# "Year Built":[form.yearBuilt.data],
# })
# print(test_case)
test_case = pd.DataFrame()
test_case["Overall Quality"] = overallquality
test_case["Squarefeet"] = area
test_case["Bedrooms"] = bedrooms
test_case["Full Baths"] = fullbaths
test_case["Garage Cars"] = garagecars
test_case["Year Built"] = yearbuilt
dummylist = []
dummylist = 15 * [0]
dummy_df = pd.DataFrame([dummylist])
test_case[[
"BldgType_1Fam", 'BldgType_2fmCon', 'BldgType_Duplex',
'BldgType_Twnhs', 'BldgType_TwnhsE', 'CentralAir_N', 'CentralAir_Y',
'HouseStyle_1.5Fin', 'HouseStyle_1.5Unf', 'HouseStyle_1Story',
'HouseStyle_2.5Fin', 'HouseStyle_2.5Unf', 'HouseStyle_2Story',
'HouseStyle_SFoyer', 'HouseStyle_SLvl'
]] = dummy_df
test_case.loc[0, buildingtype] = 1
test_case.loc[0, centralair] = 1
test_case.loc[0, housestyle] = 1
print(test_case)
prediction = model.predict(test_case)
print(prediction)
prediction = round(prediction[0], 2)
prediction = "${:,.2f}".format(prediction)
print(prediction)
return render_template("index1.html",
title="House Price Prediction",
form=form,
prediction=prediction)