Spaces:
No application file
No application file
File size: 2,896 Bytes
ecad1fd |
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 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import streamlit as st
import pandas as pd
import numpy as np
import pickle
from sklearn.ensemble import RandomForestClassifier
st.write("""
# Penguin Prediction App
This app predicts the **Palmer Penguin** species!
Data obtained from the [palmerpenguins library](https://github.com/allisonhorst/palmerpenguins) in R by Allison Horst.
""")
st.sidebar.header('User Input Features')
st.sidebar.markdown("""
[Example CSV input file](https://raw.githubusercontent.com/dataprofessor/data/master/penguins_example.csv)
""")
# Collects user input features into dataframe
uploaded_file = st.sidebar.file_uploader("Upload your input CSV file", type=["csv"])
if uploaded_file is not None:
input_df = pd.read_csv(uploaded_file)
else:
def user_input_features():
island = st.sidebar.selectbox('Island',('Biscoe','Dream','Torgersen'))
sex = st.sidebar.selectbox('Sex',('male','female'))
bill_length_mm = st.sidebar.slider('Bill length (mm)', 32.1,59.6,43.9)
bill_depth_mm = st.sidebar.slider('Bill depth (mm)', 13.1,21.5,17.2)
flipper_length_mm = st.sidebar.slider('Flipper length (mm)', 172.0,231.0,201.0)
body_mass_g = st.sidebar.slider('Body mass (g)', 2700.0,6300.0,4207.0)
data = {'island': island,
'bill_length_mm': bill_length_mm,
'bill_depth_mm': bill_depth_mm,
'flipper_length_mm': flipper_length_mm,
'body_mass_g': body_mass_g,
'sex': sex}
features = pd.DataFrame(data, index=[0])
return features
input_df = user_input_features()
# Combines user input features with entire penguins dataset
# This will be useful for the encoding phase
penguins_raw = pd.read_csv('https://raw.githubusercontent.com/dataprofessor/data/master/penguins_cleaned.csv')
penguins = penguins_raw.drop(columns=['species'], axis=1)
df = pd.concat([input_df,penguins],axis=0)
# Encoding of ordinal features
# https://www.kaggle.com/pratik1120/penguin-dataset-eda-classification-and-clustering
encode = ['sex','island']
for col in encode:
dummy = pd.get_dummies(df[col], prefix=col)
df = pd.concat([df,dummy], axis=1)
del df[col]
df = df[:1] # Selects only the first row (the user input data)
# Displays the user input features
st.subheader('User Input features')
if uploaded_file is not None:
st.write(df)
else:
st.write('Awaiting CSV file to be uploaded. Currently using example input parameters (shown below).')
st.write(df)
# Reads in saved classification model
load_clf = pickle.load(open('penguins_clf.pkl', 'rb'))
# Apply model to make predictions
prediction = load_clf.predict(df)
prediction_proba = load_clf.predict_proba(df)
st.subheader('Prediction')
penguins_species = np.array(['Adelie','Chinstrap','Gentoo'])
st.write(penguins_species[prediction])
st.subheader('Prediction Probability')
st.write(prediction_proba)
|