File size: 1,099 Bytes
a3171a2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 |
import streamlit as st
import numpy as np
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from types import NoneType
def process(data):
if type(data[0]) == NoneType or type(data[1]) == NoneType: # if either training or testing dataset is still missing
st.info('Please Upload Data')
return None
if 'object' in list(data[0].dtypes) or 'object' in list(data[1].dtypes):
st.info('Please Upload Numerica Data.')
return None
x_train = data[0].iloc[:,:-1]
y_train = data[0].iloc[:,-1]
#st.write(x_train.shape)
x_test = data[1].iloc[:,:x_train.shape[1]]
#st.dataframe(data[1])
#st.write(x_test.shape)
if len(x_train.columns) != len(x_test.columns):
st.info('Training and testing datasets have different column number, cannot perform classification.')
return None
clf = make_pipeline(StandardScaler(), SVC(gamma='auto'))
clf.fit(x_train, y_train)
pred = clf.predict(x_test)
x_test[data[0].columns[-1]] = pred
return x_test |