def predict():
form = PredictForm()
value = randint(2000, 5000)
if form.validate_on_submit():
flash(f"Prediction: {value}", "success")
return redirect(url_for("home"))
return render_template("predict.html", title="Predict", form=form)
def predict():
form = PredictForm()
if form.submit():
# NOTE: generate iam_token and retrieve ml_instance_id based on provided documentation
header = {
'Content-Type':
'application/json',
'Authorization':
'Bearer ' +
"eyJraWQiOiIyMDIwMTEyMTE4MzQiLCJhbGciOiJSUzI1NiJ9.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.bHf38EPnx79HiUky8kx48ZT3n47twChQBZ7EtMNiV6IYq26vZf9boRhl7cH2un1ec_bTn9mlTVbeR5Z9D5GejpbK6cV-bbQvAxyhQeO_8QxOakTbVjrb7XB0fJq6H0cTw3g4VgN2iPM0GmSkmUqG4nHcttkA6GIX38qTRi0vwv5Y4fq-uiQPqQEnPsm8hZ-x-slNSifNhJa9qQ4aimzkTLofihI1ou9ZugAwAr_tibZ-2pKE2q3d1MAMwomN1sUgP9SfXnZAEWcDA9tekGLdvWy828lcKcVJwXdI2jyMdq-dfVc7p6IATWYfldH7fbIhoCdzwnfpQn7hkJCSIsiNhQ",
"refresh_token":
"OKCABPadvvxWIgVb69e4uIyhyx_AnKa_gOJtx-rgeAM0m8_S1pFFoHUbvVkcBHeV9YSNK-o26jCgEPw0-Qn2aIkjZGy2jhmzOzhAXoX5KI-X_yT7c_RT-hyvsy_3oxbczx8Az0kB1y656PfhIThiOtkSw9pNvDfUFUwDwH3hsmmvHO_89LC23SCVBdto183t1Mf8kw3tyaJJvaLFs74UZ8opbeeYJ0Pnng96f_fiXdfMgemT30uZD2zFexNAsQ3SS4EyoXPhm5ZwnuuejWeHZt6d5lAAdX1Zly5FFhV4vC26aFZBOJOjyUTAQph5WbMFS4j8jyRZIbbfnM_rPSW6D6QhNr_MifPxx3wtFGQhD2tpIq220dfR_u0jWya7Ad6peNWJ8T4fzpkP9TK9XXe7CPAeRnhW_8-wq-HO3DjX20HT3Tj7xAfvw9QYyyPFb2Q56C5zg6XqHtsbAA5F9J8tCRbPcU_yjLyQzi_s_L8_Yiah5K49oWwD3M17EYNLKifQ0SKMAAGVczw9ApAqh0QBubEaMKES1559Sy5meqSslyiOAxIaAkcDB7UgrbcKiflHgdOfNXr3bGMXbDOEuOdGkGn98PQ3OSvSwxPKOA9bpZegYeoQtAWCC5mcpx7zL_Aux6mmIVhAS6q-TV0bwk7n4qUm9QTgZbnm92fkuBKvK9Kww04QC43WiqJ_1fXIAou4le9gpiZMaqXUxnZNFz7YEM1QQSxqGozA-majfeSqGRUMpk1oBLteWwn-1hDbptAxaEUZQfC__Fn6CHL-oq0t6zxEzDtvxW3knZNq38LFUevxkHAptyiAjHIo6BjGX_68-hFUeoPVXPO3SJaZkHuAPBQJ-7T0bN1eCFonkLKdxVWhdCRMrgFJULaNJ-ErVO0o4mhlnlxCaHbbpbyizsFbMai0canDQ1sykPoTlAuhKd2QYAG5MonfRPsBEMxOMIt_otgKQ5uljRZWCgjYCFdogyQ-oaEyHYCVaAvYgjhCkVYihzs6Qnv1BQ8y-pWV9j6gcBYybxm3X57x6k2Jtk0hZdbjbBko3fOE8PTnqZ4lDLTFsPUdDqkPsjS3P_W7ZpT0XEcqByZmda1pxoqdm3yt3-nfmxHVUt_fQV1lmqmnLv8Ssw"
}
python_object = [
int(form.Pregnancies.data),
int(form.Glucose.data),
int(form.BloodPressure.data),
int(form.SkinThickness.data),
int(form.Insulin.data),
float(form.BMI.data),
float(form.DiabetesPedigreeFunction.data),
int(form.Age.data)
]
#Transform python objects to Json
#print(python_object)
userInput = []
userInput.append(python_object)
# NOTE: manually define and pass the array(s) of values to be scored in the next line
payload_scoring = {
"input_data": [{
"fields": [
"Pregnancies", "Glucose", "BloodPressure", "SkinThickness",
"Insulin", "BMI", "DiabetesPedigreeFunction", "Age"
],
"values":
userInput
}]
}
#print(payload_scoring)
response_scoring = requests.post(
"https://us-south.ml.cloud.ibm.com/ml/v4/deployments/167da3fa-d770-4b95-b318-46e6b9846d5c/predictions?version=2020-12-13",
json=payload_scoring,
headers=header)
#print(response_scoring.text)
output = json.loads(response_scoring.text)
#print(output)
for key in output:
ab = output[key]
for key in ab[0]:
bc = ab[0][key]
#print(bc)
form.abc = bc[0][0] # this returns the response back to the front page
return render_template('index.html', form=form)
def pred():
form = PredictForm()
if form.is_submitted():
session['form_data'] = request.form
# for key,value in result.items():
# print(f'this is the key {key} and this is the value {value}')
print(session)
return redirect('/prediction')
return render_template('predict.html', form=form)
def bangalore():
form = PredictForm()
name = getareanames()
if form.validate_on_submit():
return redirect(url_for('test1'))
return render_template('bangalore.html',
form=form,
data=name,
title='Home')
def predictOutput():
form = PredictForm()
if form.validate_on_submit():
habitants = form.habitants.data
csvText = form.csvText.data
ht = lstmPredict(csvText, habitants)
return render_template("pages/predictOutput.html",
out=habitants,
csvText=csvText,
ht=ht)
return render_template("pages/predictOutput.html")
def predict():
form = PredictForm()
if form.submit():
# NOTE: generate iam_token and retrieve ml_instance_id based on provided documentation
header = {
'Content-Type':
'application/json',
'Authorization':
'Bearer ' +
"eyJraWQiOiIyMDIwMTEyMTE4MzQiLCJhbGciOiJSUzI1NiJ9.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.RPq2kN7AlZS6Pax_rbM2NDLRnI8DAKirOjb0U4AIZNJhN6TLi447EBqAdXd0bcAlaMYPgNZF-jHMbyLepTh0Xw_rgmpTYBDMyp7sIgDcY3thtgqC3bN_KbdrYiMa2ZnZtgmZNMED5ty71upWBZQ0FQ-_RWm7UAnuuw3QkHzm8MIKIVGU8k-oS3FXPfvZG2ktYA1d0TWIHa61t40dHTtA3re4P-YlzZFNDECiMqPcj1r6HRxaWpGjDo_aJCYuatTuhoPChT7jZ7H5VDTEfxtET3lqg3vjz1q_AsHXQnj35cjRAHadeAjgT146InWu0dTOB4f4ROSpD5kCuwQl55OPwg",
"refresh_token":
"OKBh1FV_0Z4EBaqzLLt-GqmWA-mF4pfpw6kbfS_FIhMAszPIpj_jmsnlXaT8Qj47Y0EdG_9eTrrxa-MP6B6Jvt09_wRRRX9ZSNfo-VMHo69PhfioMfBe9TDQXe7xBaBjYSjxBRfROf0WTXZVcZ5RrIw77oFHEPbFQDH6Q1iSLNBleOcTphFBIcNpG1JjTB-nopPxtAbzH4ZgTuSPflbOVYKzlTUSJELL_u1uO6wi8kgBLjNvxgby25kqtKd3wmhZbcX8HcKiA98shzMyg6ISpS41vJMrgfN11h6t-gfoEc0sq4CPqJI69W2-LoVY9CpqfG7_DmzEpyRO_DKKQx82PcvTYrEumYDbRVT1cVrZGeZgg4LGJ8e6gFldwFiiB8ZNvClJ69Rf2e5o5QQ8gpZbtY3ffthswydTsEBQ1vRF8T8AcC29LMSWNJALg5MJViomTcVqcNgTITHhWB4efpq0WJ3gSlOdDCJM_i2aITCdl4rTq3PiCa4bl6xQymCzBvsBI9DIg3Nv6G_t-Z005JofKz-pG8DRdoagotIt7uerClwbNKjqfCTE3kScwyhnFx-hFOIdjoa5Cwsmwy8A6DYR0rdMNVLU4M2DI8N7_8YJAViKvP0WJYaMr0mUPdNF-qJ2ffP4eazknnG7yilmjEq3tOZgXrpAY1k1ZdHpg0xh-1S_uyIkpG9Wr26He3u_FwNNnVki9tvPElFuDtsSXqOyoAPHB0s88jatAd_kf03fBYNW3QdNxDEr6W5-iXWW8UDdsjDGZpMYPi0OIrevnCgTpwg5QYq13l4608w85Cx14Lhm3mupzvN_pHroLIzfDW7iQWQVMq17WTBYndbLKIEea7mre1J_7xpR-W0i1yqKZwH_5vsSnlva77KXlIeW_XBVoYCHyCQeKfAOR4YUQtMINB54ZBqwyKtvBx_R68U5yqwoTf7lsXZqCPSJ34OqSHFHaTDRPEPNa3FAo8PDeEgGPdRsDuN3Q0gXgqZKs3NTF4V-odcM2jr2fzdiYq9XpmMP0Pp0Kxo29OBpfnMQYo6QbY71by9tHYIp1T7bdeDYGFwQM-pulTcV7-gjWFl4tU1dw1lShfXRFqkwFbQmqTy1DG8SWisVD3S7yyHjOP3dc2xdtg"
}
python_object = [
float(form.Wind_Speed.data),
float(form.Theoretical_Power_Curve.data),
float(form.Wind_Direction.data)
]
#Transform python objects to Json
#print(python_object)
userInput = []
userInput.append(python_object)
# NOTE: manually define and pass the array(s) of values to be scored in the next line
payload_scoring = {
"input_data": [{
"fields": [
"Wind Speed (m/s)", "Theoretical_Power_Curve (KWh)",
"Wind Direction (°)"
],
"values":
userInput
}]
}
#print(payload_scoring)
response_scoring = requests.post(
"https://us-south.ml.cloud.ibm.com/ml/v4/deployments/685d0d82-7b7c-4bcb-bf36-05446c46c097/predictions?version=2020-11-30",
json=payload_scoring,
headers=header)
print(response_scoring.text)
output = json.loads(response_scoring.text)
#print(output)
for key in output:
ab = output[key]
for key in ab[0]:
bc = ab[0][key]
form.abc = bc[0][0] # this returns the response back to the front page
return render_template('index.html', form=form)
def predict():
form = PredictForm()
if form.submit():
# NOTE: generate iam_token and retrieve ml_instance_id based on provided documentation
header = {
'Content-Type': 'application/json',
'Authorization': 'Bearer ' +
"eyJraWQiOiIyMDIwMDcyNDE4MzEiLCJhbGciOiJSUzI1NiJ9.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.Jza_BjwI9OstNsFj8G8fD3IfW3X_1_zAP1pwcUfKp-DsYxj9d07d4b2flIiM_wFjDS2ylxn7SI7nTBRGC9Fe2jMBqMUWQDkhsqA1gMJNuTzmGc-3Ik9KLLvHK56OwJjiy4UTMUL2L9tMWYufYRP0KVDLJ2qjeoGovWizqOOY5AbaMEKpnhrMIyLimPjnh5wwAtBc20BEjss5cj4WrbHmoLz4W63-jC3fHQgrLoVOm14EcS8154bkXEtHb-YbvIENOdf61PbOG5AObxkB6UxNAOGnHEuCGnb2J0l-ZUw2hCK7RIOtSxKXjKPBXdkdhHlmCd5Fg8ArtPjsshH4HKC70g",
"refresh_token":
"OKCr2IM6fK31Y5sjsLvW9tppLqlh5y4_bk1Ms-I46fJRni_uOPbQf8cblyHo40f6Y7KV4fdnkyX9cTjSSS1wi5iaK4VpxwDKEGBsl0nY8fwAw3kUtX45_ij6Me-8mxKbu9b-HGh3BQdcqmFEHwtFb4o0cO8N6LpMqxujm9xstZSs24iXpgh1JbFwKAqObeEckLuZJe7DQtZSqP3LnhU2As3KtsbPZR-bU0XrK-VVdzXZBG1hraUmtvCCMOKumvHGia-cz3nJtllIS_gsw2mrep7eLrTDY0Vnxgt0aQkfGlXZGeYe7qXiOl8eiE4Ets8--vTQFnLOQp5KJql8KXO-DcVLVviX4WHQoA0XVAlfaQrVAnGa3ngXTGXXPlixhh78WzomoyzRKXX4dWfkw5z7kaIgKacwlKEEFmzNNXqKFbMXYKqGePi-K7ntHuTnoi_D_FDmFLhMRVWh3Xo-QfWFhZUiAQP0HSbK0AMrWAQXS_H9h5PCFLzozX8ezF8fAAzf0GjDU30CWK0KdA7yYA8uP5bFlavDYI4OUksyEFxqEMRIbQIxjQg8PeJJJ666pLAyFcR--po4pe4XwLgrXe2KdzQ2ephj1DkaximHN0z_YFSKQPMiotaEUaZVkgR-i2Q_yC3ANETTQIhzQ7E9-aQ4Tvng36Qs7u8H7vT_42aEo7rIHzhooLvVaUmESCFtYdNeGmk4g1LY5SmYbNe-dHQ1UEJrXPAfiXbvFMc0GWfdO_-VBPbmQgVLtLM6i5ywwdzfxu0d2y-OLFqrfB-n5jdN4S8VZdjAxDu8VR46MJRahBWIwswa7T2Q0zB9OjL1q5q7ddrXabQTFu3Jxazrapj7XsBt3uHQ6a6nF8LIb5gBktDNEsFs6XIk-e9TIzwJImsErsa9b95kKWunQr3Tom5idhsUkRMScxZUNllUGopOtfTyAR_kNkBykKsDMtKoBTY6BTEy_TIuOZLFWOGEWDSojwms_ctvwfBzAUD0mT2W20gw53sqNsozpJpbFqplYSP5at6R3I3EQ3s9M96Iu_2Y6PV8uszXd0eucxvgY27orq6fdP6MMEqShf3ScFgVQNEGiSc",
'ML-Instance-ID': "61862e37-c7bc-4fae-9d6e-5dc33e3d5700"
}
if (form.ID_Txn.data == None):
python_object = []
else:
#float(form.bmi.data)
python_object = [
int(form.ID_Txn.data), form.Hora_Txn.data, form.Sexo.data,
form.Edo_Civil.data, form.Hijos.data, form.Monto_Txn.data,
form.Establecimiento.data, form.Tipo_Compra.data,
form.Metodo_Pago.data, form.Edad.data
]
#Transform python objects to Json
userInput = []
userInput.append(python_object)
# NOTE: manually define and pass the array(s) of values to be scored in the next line
payload_scoring = {
"input_data": [{
"fields": [
"ID_Txn", "Hora_Txn", "Sexo", "Edo_Civil", "Hijos",
"Monto_Txn", "Establecimiento", "Tipo_Compra",
"Metodo_Pago", "Edad"
],
"values":
userInput
}]
}
response_scoring = requests.post(
"https://us-south.ml.cloud.ibm.com/v4/deployments/4c8b8b97-954b-4238-b09c-1d9276f8a39d/predictions",
json=payload_scoring,
headers=header)
output = json.loads(response_scoring.text)
print(output)
form.abc = output # this returns the response back to the front page
return render_template('index.html', form=form)
def predict():
form = PredictForm()
if form.submit():
# NOTE: generate iam_token and retrieve ml_instance_id based on provided documentation
header = {
'Content-Type': 'application/json',
'Authorization':
'Bearer ' + " TODO: ADD YOUR IAM ACCESS TOKEN FROM IBM CLOUD HERE",
'ML-Instance-ID': " TODO: ADD YOUR ML INSTANCE ID HERE "
}
if (form.bmi.data == None):
python_object = []
else:
python_object = [
form.age.data, form.sex.data,
float(form.bmi.data), form.children.data, form.smoker.data,
form.region.data
]
#Transform python objects to Json
userInput = []
userInput.append(python_object)
# NOTE: manually define and pass the array(s) of values to be scored in the next line
payload_scoring = {
"input_data": [{
"fields":
["age", "sex", "bmi", "children", "smoker", "region"],
"values":
userInput
}]
}
response_scoring = requests.post(
"https://us-south.ml.cloud.ibm.com/v4/deployments/ADD-DEPLOYMENT-ID-HERE/predictions",
json=payload_scoring,
headers=header)
output = json.loads(response_scoring.text)
for key in output:
ab = output[key]
for key in ab[0]:
bc = ab[0][key]
roundedCharge = round(bc[0][0], 2)
form.abc = roundedCharge # this returns the response back to the front page
return render_template('index.html', form=form)
def predict():
form = PredictForm()
if form.submit():
# NOTE: you should not use your apikey in plain text consider using iam_token directly in PROD enviroments.
API_KEY = "j_iFO1lfw14_IltudzUFHu-2IElu32oM1ip1pzsJTb77"
token_response = requests.post('https://iam.cloud.ibm.com/identity/token', data={"apikey": API_KEY, "grant_type": 'urn:ibm:params:oauth:grant-type:apikey'})
mltoken = token_response.json()["access_token"]
# NOTE: generate iam_token and retrieve ml_instance_id based on provided documentation
header = {'Content-Type': 'application/json', 'Authorization': 'Bearer ' + "eyJraWQiOiIyMDIxMDQyMDE4MzYiLCJhbGciOiJSUzI1NiJ9.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.Of3dCuqM-reK7X9CGqlss1lJ7L8sJL5TbWfLTLkHcTZ7B8f2iht7FyUx6RNIE5jTArIBlO7ni4BRyMVR4dFOeUs0-U9uPdiupPdtnCHA2XnMpaLDPE7vNNgeLyqs1AEaKm_4U7MRMTWdVwQxFCbFoK1fuu1Z-Cw5r_CErpu1ucaooNQneLa4ejYL-Vh3DpLGcCF-kQjaJFxiBZvcfr2TGbFHS4Cr68FZ4lSFgztxF7id0dEhT7kO8Vk7bfftdfFrwzYHXuTaK0Gdly_3GU4bjz6b4vnixqS9iG_fcjsrwF8BGAoAHo-8khvmHPCjV_QLgNcsNfN8ze_MrymLcFgggA"}
if(form.MesVencimiento.data == None):
python_object = []
else:
# form.Unnamed=1
python_object = [form.Unnamed.data,form.Cliente.data, form.Pais.data,form.Moneda.data,form.Unidad.data,
form.MesVencimiento.data,form.Monto.data, form.plazo.data,float(form.Prob_D.data)]
#Transform python objects to Json
userInput = []
userInput.append(python_object)
# NOTE: manually define and pass the array(s) of values to be scored in the next line
payload_scoring = {"input_data": [{"fields": ["Unnamed: 0",
"Cliente",
"Pais",
"Moneda",
"Unidad",
"MesVencimiento",
"Monto",
"plazo",
"Prob_D"], "values": userInput }]}
response_scoring = requests.post("https://us-south.ml.cloud.ibm.com/ml/v4/deployments/37264cc6-49e9-496a-bf4e-a955f07affe4/predictions?version=2021-05-01", json=payload_scoring, headers=header)
output = json.loads(response_scoring.text)
print(output)
for key in output:
ab = output[key]
for key in ab[0]:
bc = ab[0][key]
roundedCharge = round(bc[0][0],2)
if roundedCharge == 1 :
respuesta="Si entrara en default"
else:
respuesta="Es probable que no entre en default"
form.abc = respuesta # this returns the response back to the front page
form.ammount=form.Prob_D.data*form.Monto.data
return render_template('index.html', form=form)
def predict():
form = PredictForm()
if form.submit():
# NOTE: generate iam_token and retrieve ml_instance_id based on provided documentation
header = {
'Content-Type':
'application/json',
'Authorization':
'Bearer ' +
"eyJraWQiOiIyMDIwMTEyMTE4MzQiLCJhbGciOiJSUzI1NiJ9.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.aRyTDRa4-m6jMdsStWtrOI51oVewxDAPaUDykEU6L4B75Q3eWJ5BcmKavKFKwXhySrs4XUpU1zAxTr7-l5awLMYJVoLfR2L7wC7_GlDTShEPSvoX_jUyyekMMKzAIshP_utV5LzEhJs4klzBLOfSuQTlh49PKodhGPIy8njEnLSbPu-NRwb01W-E3si2I1w3wPM_u_gUCnWPBljThaoLrLC28VqSDOFL67H2fK-lpVsKFV5j-P14g7dm2ckdxqUYFrhIgeAKdHtAuHx1njXaffo0dAZmooYaaP_6gI_Ajh1WFgegeAnfkA7kEpvYaQIQN07SEgmnMRrYVXdO_xx8rQ"
}
python_object = [
float(form.Wind_Speed.data),
float(form.Theoretical_Power_Curve.data),
float(form.Wind_Direction.data)
]
#Transform python objects to Json
#print(python_object)
userInput = []
userInput.append(python_object)
# NOTE: manually define and pass the array(s) of values to be scored in the next line
payload_scoring = {
"input_data": [{
"fields": [
"Wind Speed (m/s)", "Theoretical_Power_Curve (KWh)",
"Wind Direction (°)"
],
"values":
userInput
}]
}
#print(payload_scoring)
response_scoring = requests.post(
"https://us-south.ml.cloud.ibm.com/ml/v4/deployments/e42cf888-7ee0-4a9c-bddc-3c4adf3fa2cb/predictions?version=2020-12-14",
json=payload_scoring,
headers=header)
print(response_scoring.text)
output = json.loads(response_scoring.text)
#print(output)
for key in output:
ab = output[key]
for key in ab[0]:
bc = ab[0][key]
form.abc = bc[0][0] # this returns the response back to the front page
return render_template('index.html', form=form)
def predict():
form = PredictForm()
if form.validate_on_submit():
sex,exang,ca,cp,restecg,slope,thal = form.data['sex'],\
form.data['exang'],\
form.data['ca'],\
form.data['cp'],\
form.data['restecg'],\
form.data['slope'],\
form.data['thal']
flash("Have Heart Disease" if prediction(sex,exang,ca,cp,restecg,slope,thal)\
else "No Heart Disease" ,'success')
return render_template('predict.html',
title='predict the heart disease',
form=form)
def home():
form = PredictForm()
if form.validate_on_submit():
cleaned = pattern.sub(' ', form.example.data.lower())
new_examples = [cleaned]
predictions, probs = classifier.predict(new_examples)
return render_template('result.html',
max_coef=classifier.get_max_coefficient(),
words=classifier.get_coefficients_for(
new_examples[0]),
example=new_examples[0],
pos_prob=probs[1],
neg_prob=probs[0],
form=TrainForm())
return render_template('index.html', form=form)
def home():
form = PredictForm()
if form.validate_on_submit():
cleaned = pattern.sub(' ', form.example.data.lower())
new_examples = [cleaned]
predictions, probs = classifier.predict(new_examples)
return render_template('result.html',
max_coef = classifier.get_max_coefficient(),
words = classifier.get_coefficients_for(new_examples[0]),
example = new_examples[0],
pos_prob = probs[1],
neg_prob = probs[0],
form = TrainForm())
return render_template('index.html',
form = form)
def linear():
form = PredictForm()
if form.validate_on_submit():
stock = request.form["stockTicker"]
days = int(request.form["daysToPredict"])
stock_csv(stock)
prediction = predictPrice(stock, days)
if (days == 1):
flash("Linear Regression | " + str(stock) + "'s High in " +
str(days) + " day will be: $" +
str(round(prediction[0], 2)) + ".")
else:
flash("Linear Regression | " + str(stock) + "'s High in " +
str(days) + " days will be: $" +
str(round(prediction[0], 2)) + ".")
return render_template('linear.html', title='Linear Regression', form=form)
def predict():
form = PredictForm()
if form.submit():
#API_KEY = "<IBM Cloud API key>" #Select Account > Users, go to Manage > Access (IAM) > API keys.
API_KEY = "GjBEDX7Pq5jMNaP97G9XbYDX_nhU2EO3HOgRvYibRFg6"
token_response = requests.post('https://iam.cloud.ibm.com/identity/token', data={"apikey": API_KEY, "grant_type": 'urn:ibm:params:oauth:grant-type:apikey'})
mltoken = token_response.json()["access_token"]
header = {'Content-Type': 'application/json', 'Authorization': 'Bearer ' + mltoken}
if( form.case.data == None and form.symptoms_start_date.data == None and form.diagnosys_date.data == None and
form.city.data == None and form.locality.data == None and form.age.data == None and form.age_unit.data == None and form.sex.data == None and
form.contagion_type.data == None and form.current_location.data == None ):
python_object = []
else:
python_object = [form.case.data, form.symptoms_start_date.data, form.diagnosys_date.data,
form.city.data, form.locality.data, form.age.data, form.age_unit.data, form.sex.data,
form.contagion_type.data, form.current_location.data ]
#Transform python objects to Json
userInput = []
userInput.append(python_object)
# NOTE: manually define and pass the array(s) of values to be scored in the next line
payload_scoring = {"input_data": [{"fields": ["case", "symptoms_start_date", "diagnosys_date",
"city", "locality", "age", "age_unit", "sex", "contagion_type", "current_location" ], "values": userInput }]}
print(payload_scoring)
# response_scoring = requests.post("https://us-south.ml.cloud.ibm.com/ml/v4/deployments/<deployment-id-goes-here>/predictions?version=<DATE>", json=payload_scoring, headers=header)
response_scoring = requests.post('https://us-south.ml.cloud.ibm.com/ml/v4/deployments/2aa265c9-4684-4ae6-8d75-fd998592f5b8/predictions?version=2021-04-30', json=payload_scoring, headers={'Authorization': 'Bearer ' + mltoken})
output = json.loads(response_scoring.text)
print("Salida")
print(output)
print("Salida")
form.abc = ""
if 'predictions' in output.keys():
ab = output['predictions']
for key in ab[0]:
bc = ab[0][key]
# form.abc = roundedCharge # this returns the response back to the front page
form.abc = bc[0][0] # this returns the response back to the front page
return render_template('index.html', form=form)
def defectpredict():
formPredict=DefectPrediction()
form = PredictForm()
if formPredict.submit():
print(formPredict.plannedCP.data)
print(formPredict.teamExpertise.data)
print(formPredict.efforts.data)
# NOTE: generate iam_token and retrieve ml_instance_id based on provided documentation
header = {'Content-Type': 'application/json', 'Authorization': 'Bearer '
+ "eyJraWQiOiIyMDIwMDgyMzE4MzIiLCJhbGciOiJSUzI1NiJ9.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.PV9-vkONx0bPJx9pMrBO1ojYjxpQKzJidqKng_17SXwSUDzylcYdbLUnlfKOsFhueWpELQP-l7qXkH0MlXC4QCiGicBRRj9xx-khQNkvOyYHfuX6X_dNgkLa_QGexLk28Z49wIFlnce2FzPkA67Dn9uyynBkZCsSf_agVRBeKhVqJKea4MS1Zfyu8BQMLLA3XJANIy58rJABw4bhOQ74cFISrQ8778INA2VGztQRWUM4FmaRofJCpYx_Cg4TP-KylBW_BFLSMnVZGnYcCEK1PI72vrOl9B7DkPwNX7aSc5dh4VfzMGSaQqrlTnpf6Ld0DJwkciQHH79-MeMpsAXVpA",
'ML-Instance-ID': "91acd4b0-3679-4e9e-9d59-d251f0645d1d"}
BaseLinedEPCP = decimal.Decimal(1.5)
TeamExpertise = formPredict.teamExpertise.data
Efforts = formPredict.efforts.data
ActualEPCP = Efforts/formPredict.plannedCP.data
global VarianceRiskFactor
global ComplexityFactor
VarianceRiskFactor = 0
if ActualEPCP <= BaseLinedEPCP:
VarianceRiskFactor = 0
elif ActualEPCP - BaseLinedEPCP >0 and ActualEPCP - BaseLinedEPCP<=0.5:
VarianceRiskFactor = 1.25
elif ActualEPCP - BaseLinedEPCP >0.5 and ActualEPCP - BaseLinedEPCP<=1:
VarianceRiskFactor = 3
elif ActualEPCP - BaseLinedEPCP >1 and ActualEPCP - BaseLinedEPCP<=1:
VarianceRiskFactor = 5
ComplexityFactor = 0.7 * VarianceRiskFactor + 0.3 * TeamExpertise
print(ComplexityFactor)
formPredict.complexityFactor.data=ComplexityFactor
python_object = [float(formPredict.efforts.data),float(formPredict.plannedCP.data), formPredict.teamExpertise.data,float(formPredict.complexityFactor.data)]
#Transform python objects to Json
userInput = []
userInput.append(python_object)
# NOTE: manually define and pass the array(s) of values to be scored in the next line
payload_scoring = {"input_data": [{"fields": ["efforts", "plannedCP", "teamExpertise","complexityFactor"], "values": userInput }]}
response_scoring = requests.post('https://private.eu-gb.ml.cloud.ibm.com/ml/v4/deployments/e16087e9-ba37-4642-9e02-3254e38b77cf/predictions', json=payload_scoring, headers=header)
output = json.loads(response_scoring.text)
print(output)
formPredict.result=output
return render_template('index.html', form=form,formPredict=formPredict)
def predict():
form = PredictForm()
if form.submit():
# NOTE: you should not use your apikey in plain text consider using iam_token directly in PROD enviroments.
API_KEY = "<Your APIKEY here>"
token_response = requests.post('https://iam.cloud.ibm.com/identity/token', data={"apikey": API_KEY, "grant_type": 'urn:ibm:params:oauth:grant-type:apikey'})
mltoken = token_response.json()["access_token"]
# NOTE: generate iam_token and retrieve ml_instance_id based on provided documentation
header = {'Content-Type': 'application/json', 'Authorization': 'Bearer ' + mltoken}
if(form.bmi.data == None):
python_object = []
else:
python_object = [form.age.data, form.sex.data, float(form.bmi.data),
form.children.data, form.smoker.data, form.region.data]
#Transform python objects to Json
userInput = []
userInput.append(python_object)
# NOTE: manually define and pass the array(s) of values to be scored in the next line
payload_scoring = {"input_data": [{"fields": ["age", "sex", "bmi",
"children", "smoker", "region"], "values": userInput }]}
response_scoring = requests.post("https://us-south.ml.cloud.ibm.com/ml/v4/deployments/<Your deployment ID here>/predictions?version=2020-09-01", json=payload_scoring, headers=header)
output = json.loads(response_scoring.text)
print(output)
for key in output:
ab = output[key]
for key in ab[0]:
bc = ab[0][key]
roundedCharge = round(bc[0][0],2)
form.abc = roundedCharge # this returns the response back to the front page
return render_template('index.html', form=form)
def predict():
form = PredictForm()
if form.submit():
# NOTE: generate iam_token and retrieve ml_instance_id based on provided documentation
header = {'Content-Type': 'application/json', 'Authorization': 'Bearer '
+ "eyJraWQiOiIyMDIwMDUyNTE4MzAiLCJhbGciOiJSUzI1NiJ9.eyJpYW1faWQiOiJpYW0tU2VydmljZUlkLTIzMWI5OTYyLWExN2ItNDI3OC05YmY3LTQ3Y2RkMDgwYjc2ZCIsImlkIjoiaWFtLVNlcnZpY2VJZC0yMzFiOTk2Mi1hMTdiLTQyNzgtOWJmNy00N2NkZDA4MGI3NmQiLCJyZWFsbWlkIjoiaWFtIiwiaWRlbnRpZmllciI6IlNlcnZpY2VJZC0yMzFiOTk2Mi1hMTdiLTQyNzgtOWJmNy00N2NkZDA4MGI3NmQiLCJuYW1lIjoid2RwLXdyaXRlciIsInN1YiI6IlNlcnZpY2VJZC0yMzFiOTk2Mi1hMTdiLTQyNzgtOWJmNy00N2NkZDA4MGI3NmQiLCJzdWJfdHlwZSI6IlNlcnZpY2VJZCIsImFjY291bnQiOnsidmFsaWQiOnRydWUsImJzcyI6IjkzZWFmZDU2MjNlYTRjMGFhNWYwOWVmOTQ1MjkxOGEyIn0sImlhdCI6MTU5MTYzMTIxOCwiZXhwIjoxNTkxNjM0ODE4LCJpc3MiOiJodHRwczovL2lhbS5ibHVlbWl4Lm5ldC9pZGVudGl0eSIsImdyYW50X3R5cGUiOiJ1cm46aWJtOnBhcmFtczpvYXV0aDpncmFudC10eXBlOmFwaWtleSIsInNjb3BlIjoiaWJtIG9wZW5pZCIsImNsaWVudF9pZCI6ImRlZmF1bHQiLCJhY3IiOjEsImFtciI6WyJwd2QiXX0.irk9heVcOtqTkLLWsYoQFM_hP_fjSVDgaxN7letIojAQUSuQUPW2YlVLoWTTQUIVw5vuvQC75JxBhP7OzFRjI87a7AEkrUN30BjACaLLTs8DM6xBA2hJc74enoi3lJ4dDhIlDt_yeCh0oBxxu14R6jqCP9Vem47mhJ1GaVFM9M5n4sT25PnAcG_u35DDC81GIYbhdFedE1IAI8roxplH2B0ZVqWjfHL5E2feZ37mM1e5QFl4Y_5p6T5kbjeb12kneAEegkS56obfG3V4ymOzv-r_RJZT8zSP4gxT6cskOZ2IpExgXi4AMXRvC6-5mwOLXMJJ2ZUkGinZjtV0HGl9uA","refresh_token":"OKCQYya-8VbNzh7hW0khQVl3S6qk4aBciH2DX77fW9_YQxyfvFzdjIMX1D8DmHICPI-G86hLGlZduLSC_Occ5VeoiRW_GiCOs6CtdI10VgRhnVgowy5sYPf3z6KQfWJX6hmZu004ka2VWvMCF8VcqqasO-1ZACJX2xfn_NNrR2titFudDlZCyUqC8IeqJ5YAgW8rZlyw7lBXxN4M_A9m7v3p2L2QJS71SBKm8FjIDyp7b0QX_lpPW2mGlFl18cemHp_fciuWGlTt-XyiMbpJuHFkSxSVrjfpyRlgBmqfyUZnii8cQDLydxexS08SQZ6zmtW-KmYCzy6Zb1xsQYeQnSLoaJTPpHtRro5yN0L9aC_tSM9BwMrMLQ_ZiWYxKqnApghFdc6QCpVoxAsqs4uXozgpafDA99Ww0x49ssDw9_tdJ8uUJWQH24Gkqvl_ePJT1-IgTvIVAbM1zwEWiuAT6AXc60Kwm-8qypokkng1AE_djkeK5epOFo70jKHTPhUEy-pscBezOttQ2-noORZJTrkifePlkfiEI05FxGDZiix1NV0Mf2TTRcdQnEYtgVLzUx9SZdUrpBb09rNIvGrMtdXBg-Fy1qhPMi_90MXO1y1Dn6CcwVVp2my7WMuIQswWQ43nwpfkyAML_yk3bvekl1dTGVYKpJvDnuqJzEW4vZ_iAbInQHwHsXIpmVCaFBw1ZuMjOQZ14dz_ugvkI7sy0N0P0SuFM5Ppx_07H2X5bcQa3CQRWYSOM9DdCcHhojE8xvgQzpTOPBvayoA58DosN03r7Jffz0wtAow4kYPl8_GQYfFA5t5AUONNHrIe7RC1d76NAZBSJElgQzdv7oQIdSAdjAKUR3B1WJ-LcmiX2wFoaR0-Ecxhgo130-J0BCbHoRk73OSxGmFfHVNPVlo0wbpYbOLOgdMBisCkRsmh1eI54OKPSXkuJ-LjXHyALIxu9ewhkuj-eKo_IXSMwmBDN1Z3rMvA3GQu8hcWjxZYcVb5DU_0-M-3ZMPYm8BNd9-Swwmh3bUtpe3u9PkAN4k_I0GOknwJp8nAANsBNHeoxi64rw",
'ML-Instance-ID': "9c3b2402-9562-439e-8df2-9545ed40c34a"}
if(form.ingreso_mensual.data == None):
python_object = []
else:
python_object = [form.edad.data, form.estado_civil.data, float(form.ingreso_mensual.data),
form.anios_laboral.data, form.hijos.data, form.region.data]
#Transform python objects to Json
userInput = []
userInput.append(python_object)
# NOTE: manually define and pass the array(s) of values to be scored in the next line
payload_scoring = {"input_data": [{"fields": ["edad", "estado_civil", "ingreso_mensual",
"anios_laboral", "hijos", "region"], "values": userInput }]}
response_scoring = requests.post("https://us-south.ml.cloud.ibm.com/v4/deployments/c2f3ae93-dfce-4ce6-8eb5-9378209a7e35/predictions", json=payload_scoring, headers=header)
output = json.loads(response_scoring.text)
print(output)
for key in output:
ab = output[key]
for key in ab[1]:
bc = ab[0][key]
roundedCharge = round(bc[0][0],2)
form.abc = roundedCharge # this returns the response back to the front page
return render_template('index.html', form=form)
def indexfunc():
form=PredictForm()
model = keras.models.load_model("hospital_model.h5")
transformer = joblib.load("data_transformer.joblib")
prediction_text='Result will appear here...'
if form.validate_on_submit():
newdict={
'age': [str(form.age.data)],
'time_in_hospital': [int(form.time_in_hospital.data)],
'num_medications': [int(form.num_medications.data)],
'number_diagnoses': [int(form.number_diagnoses.data)],
'metformin':[str(form.metformin.data)],
'chlorpropamide':[str(form.chlorpropamide.data)],
'glimepiride':[str(form.glimepiride.data)],
'tolazamide':[str(form.tolazamide.data)],
'insulin':[str(form.insulin.data)],
'race':[str(form.race.data)],
'admission_type_id':[int(form.admission_type_id.data)],
'admission_source_id':[int(form.admission_source_id.data)],
'max_glu_serum':[str(form.max_glu_serum.data)],
'A1Cresult':[str(form.A1Cresult.data)]
}
newds=pd.DataFrame(newdict)
prediction = model.predict(transformer.transform(newds))
max_index_col = np.argmax(prediction, axis=1)
if max_index_col==0:
prediction_text=' The Patient will be readmitted more than 30 Times '
if max_index_col==1:
prediction_text=' The Patient will be readmitted less than 30 Times '
if max_index_col==2:
prediction_text=' The Patient will be not be readmitted '
return render_template('regression.html', form=form,prediction_text=prediction_text)
def test():
form = PredictForm()
name = getareanames()
select = request.form.get('comp_select')
AreaNo = name.Area_Names[select]
with open('./Resources/chennaihousepredictionpickle.pickle', 'rb') as f:
model = pickle.load(f)
predict = int(
model.predict(
[[AreaNo, form.INTSQFT.data, form.BHK.data, form.BATHROOMS.data]]))
data2 = ("AREA", select, " AREA NO", AreaNo, "Square feet",
form.INTSQFT.data, "BHK", form.BHK.data, "BATHROOMS",
form.BATHROOMS.data)
return render_template('test.html', data=predict, data2=data2)
def predict():
# get iris object from request
# X = request.get_json()
# X = [[float(X['sepalLength']), float(X['sepalWidth']), float(X['petalLength']), float(X['petalWidth'])]]
# # read model
# clf = joblib.load('model.pkl')
# probabilities = clf.predict_proba(X)
probabilities = 0
form = PredictForm()
if request.method == 'POST':
flash(f'Prediction Created', 'success')
clf = joblib.load('model.pkl')
# algorithm = request.form['algorithm']
clump_thickness = request.form['clump_thickness']
uniformity_of_cell_size = request.form['uniformity_of_cell_size']
uniformity_of_cell_shape = request.form['uniformity_of_cell_shape']
marginal_adhesion = request.form['marginal_adhesion']
single_epithelial_cell_size = request.form[
'single_epithelial_cell_size']
bare_nuclei = request.form['bare_nuclei']
bland_chromatin = request.form['bland_chromatin']
normal_nucleoli = request.form['normal_nucleoli']
mitoses = request.form['mitoses']
X = np.array([[
clump_thickness, uniformity_of_cell_size, uniformity_of_cell_shape,
marginal_adhesion, single_epithelial_cell_size, bare_nuclei,
bland_chromatin, normal_nucleoli, mitoses
]])
prediction = clf.predict(X)
# test = np.array([[5,1,1,1,2,1,3,1,1],[8,10,10,8,7,10,9,7,1]])
# prediction = clf.predict_proba(test)
print(prediction)
return render_template('predict.html',
title='Predict',
form=form,
probabilities=prediction)
return render_template('predict.html',
title='Predict',
form=form,
probabilities=[])
def startApp():
form = PredictForm()
return render_template('index.html', form=form)
def predict():
form = PredictForm()
formPredict = DefectPrediction()
if form.submit():
SearchStr = form.num1.data
k = 0
if (not re.sub('[^A-Za-z0-9]+', '', SearchStr)):
output = "Invalid Input"
else:
print("Anushree!!!")
for a in df.index:
X = df['Desc'][a]
# tokenization
X_list = word_tokenize(X.lower())
Y_list = word_tokenize(SearchStr.lower())
# Fetching all stop words
sw = stopwords.words('english')
V1 = []
V2 = []
# Stop word removal
X_set = {lemmatizer.lemmatize(w) for w in X_list if not w in sw}
Y_set = {lemmatizer.lemmatize(w) for w in Y_list if not w in sw}
UV = X_set.union(Y_set)
for w in UV:
if w in X_set: V1.append(1)
else: V1.append(0)
if w in Y_set: V2.append(1)
else: V2.append(0)
c = 0
# Calculating cosine similarity
for i in range(len(UV)):
c += V1[i] * V2[i]
cosine = c / float((sum(V1) * sum(V2))**0.5)
Final.loc[Final['Defect Description'] == X, 'Similarity'] = cosine
df_Final = Final.copy()
#sum=form.num1.data+form.num2.data
df_Final = Final[(Final['Similarity'] > 0)].sort_values(
by='Similarity', ascending=False)
df_Final = df_Final.drop_duplicates(subset=['Defect Description'],
keep='first')
df_Final = df_Final[[
'Release Name', 'Defect ID', 'Defect Description', 'RCA'
]].head(3)
#print(df_Final)
#df_Final=pd.DataFrame.to_html(df_Final,columns={'Similarity','Defect_desc'},index=False,classes='data')
#df_Final=pd.DataFrame.to_records(df_Final,index=False)
#form.pd=df_Final
output = df_Final.to_html(classes='data',
header="true",
index=False)
#display(HTML(form.abc))
#print(form.abc)
return render_template('index.html',
form=form,
formPredict=formPredict,
tables=[output])
def predict():
form = PredictForm()
return render_template("pages/predict.html", form=form)
def startApp():
form = PredictForm()
formPredict = DefectPrediction()
return render_template('index.html', form=form, formPredict=formPredict)
def predict():
form = PredictForm()
if form.submit():
SearchStr=form.num1.data
TOD="Business Logic"
k=0
for a in df.index:
X=df['Desc'][a]
# tokenization
X_list = word_tokenize(X.lower())
Y_list = word_tokenize(SearchStr.lower())
# Fetching all stop words
sw = stopwords.words('english')
V1 =[];V2 =[]
# Stop word removal
X_set = {lemmatizer.lemmatize(w) for w in X_list if not w in sw}
Y_set = {lemmatizer.lemmatize(w) for w in Y_list if not w in sw}
UV = X_set.union(Y_set)
for w in UV:
if w in X_set: V1.append(1)
else: V1.append(0)
if w in Y_set: V2.append(1)
else: V2.append(0)
c = 0
# Calculating cosine similarity
for i in range(len(UV)):
c+= V1[i]*V2[i]
cosine = c / float((sum(V1)*sum(V2))**0.5)
Final.loc[Final['Defect_desc']== X,'Similarity']=cosine
df_Final=Final.copy()
#sum=form.num1.data+form.num2.data
df_Final=Final[(Final['Similarity']>0) & (Final['Type of Defect']==TOD)].sort_values(by='Similarity',ascending=False).head(3).head(3)
#print(df_Final)
df_Final=pd.DataFrame.to_html(df_Final)
#print(df_Final)
form.abc=df_Final
#print(form.abc)
pd.show_versions()
return render_template('index.html', form=form)
def predict():
form = PredictForm()
if form.submit():
if (form.antigen.data == None):
python_object = []
else:
python_object = [
int(form.patient_age_quantile.data),
int(form.patient_addmited_to_regular.data),
int(form.patient_addmited_to_semi_intense.data),
int(form.patient_addmited_to_intense.data),
float(form.platelets.data),
float(form.mean_platelet_volume.data),
float(form.red_blood_cells.data),
float(form.lymphocytes.data),
float(form.mean_corpuscular_hemoglobin_concentration.data),
float(form.leukocytes.data),
float(form.basophils.data),
float(form.eosinophils.data),
float(form.mean_corpuscular_volum.data),
float(form.monocytes.data),
float(form.red_blood_cell_distribution_width.data),
int(form.antigen.data)
]
#Transform python objects to Json
userInput = []
userInput.append(python_object)
# # NOTE: manually define and pass the array(s) of values to be scored in the next line
test_value = {
"input_data": [{
"fields": [
"patient_age_quantile", "patient_addmited_to_regular",
"patient_addmited_to_semi_intense",
"patient_addmited_to_intense", "platelets",
"mean_platelet_volume", "red_blood_cells", "lymphocytes",
"mean_corpuscular_hemoglobin_concentration", "leukocytes",
"basophils", "eosinophils", "mean_corpuscular_volum",
"monocytes", "red_blood_cell_distribution_width", "antigen"
],
"values":
userInput
}]
}
test_value["input_data"][0]["values"][0][0] = get_age(
int(test_value["input_data"][0]["values"][0][0]))
print(test_value)
output = makeRequest(test_value, _run_on_start.first_token)
for key in output:
ab = output[key]
for key in ab[0]:
bc = ab[0][key]
if (bc[0][0] == 0):
result = "Negative to Covid-19 Test"
confident = "Condifident of : " + str(round(bc[0][1][0], 3))
else:
result = "Positve to Covid-19 Test "
confident = "Condifident of : " + str(round(bc[0][1][1], 3))
print(result)
form.abc = result
form.confi = confident
return render_template('index.html', form=form)
def predict():
form = PredictForm()
if form.submit():
# Replace the following key with the IAM Key that you have generated.
iamkey = 'YOUR IAM KEY GOES HERE'
deployment_id = 'YOUR DEPLOYMENT ID GOES HERE'
iam_token_response = requests.post(
'https://iam.cloud.ibm.com/oidc/token',
headers={'Content-Type': 'application/x-www-form-urlencoded'},
data={
'grant_type': 'urn:ibm:params:oauth:grant-type:apikey',
'apikey': iamkey
})
iam_token_response_json = json.loads(iam_token_response.text)
iam_token = iam_token_response_json["access_token"]
header = {
'Content-Type': 'application/json',
'Authorization': 'Bearer ' + iam_token
}
if (form.bmi.data == None):
python_object = []
else:
python_object = [
int(form.pregnancies.data),
int(form.glucose.data),
int(form.bloodpressure.data),
int(form.skinthickness.data),
int(form.insulin.data),
float(form.bmi.data),
float(form.diabetespedigreefunction.data),
int(form.age.data)
]
userInput = []
userInput.append(python_object)
payload_json = {
"input_data": [{
"fields": [
"Pregnancies", "Glucose", "BloodPressure", "SkinThickness",
"Insulin", "BMI", "DiabetesPedigreeFunction", "Age"
],
"values":
userInput
}]
}
response_scoring = requests.post(
f"https://eu-gb.ml.cloud.ibm.com/ml/v4/deployments/{deployment_id}/predictions?version=2021-04-23",
json=payload_json,
headers=header)
output = json.loads(response_scoring.text)
for key in output:
opt = output[key]
for key in opt[0]:
bc = opt[0][key]
roundedResult = round(bc[0][0], 2)
if roundedResult == 1:
msg = "Positive - Susceptible to Diabetes"
else:
msg = "Negative - Not Susceptible to Diabetes"
form.outcome = msg
return render_template('index.html', form=form)