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)