Upload 3 files

app.py

@@ -0,0 +1,79 @@
+from operator import index
+import streamlit as st
+import plotly.express as px
+import numpy as np
+from pycaret.regression import setup, compare_models, pull, save_model, load_model, plot_model
+# from lazypredict.Supervised import LazyRegressor
+# from sklearn.model_selection import train_test_split
+from pandas_profiling import ProfileReport
+import pandas as pd
+from streamlit_pandas_profiling import st_profile_report
+import os 
+
+@st.cache
+def load_data():
+    return pd.read_csv('dataset.csv', index_col=None)
+
+# Rest of your code...
+
+if os.path.exists('./dataset.csv'): 
+    df = load_data()
+
+with st.sidebar: 
+    st.image("https://michael-fuchs-python.netlify.app/post/2022-01-01-automl-using-pycaret-classification_files/p133s1.png")
+    st.title("AutoML")
+    choice = st.radio("Navigation", ["Upload","Profiling","Modelling", "Download"])
+    st.info("This project application helps you build and explore your data.")
+
+if choice == "Upload":
+    st.title("Upload Your Dataset")
+    file = st.file_uploader("Upload Your Dataset")
+    if file: 
+        df = pd.read_csv(file, index_col=None)
+        df.to_csv('dataset.csv', index=None)
+        st.dataframe(df)
+
+if choice == "Profiling": 
+    st.title("Exploratory Data Analysis")
+    profile_df = df.profile_report()
+    st_profile_report(profile_df)
+
+if choice == "Modelling": 
+    chosen_target = st.selectbox('Choose the Target Column', df.columns)
+    if st.button('Run Modelling'): 
+        print("WIP")
+        # h2o.init()
+        # df = h2o.import_file(df)
+        # df.describe(chunk_summary=True)
+        # train, test = df.split_frame(ratios=[0.8], seed = 1)
+        # aml = H2OAutoML(max_models =25,
+        #         balance_classes=True,
+		# seed =16548846)
+        # aml.train(training_frame = train, y = 'y')
+        # lb = aml.leaderboard
+        # lb.head(rows=lb.nrows)
+        # aml.train(training_frame = train, y = 'y', leaderboard_frame = my_leaderboard_frame)
+        # best_model = aml.get_best_model()
+        # model_path = h2o.save_model(model=best_model,force=True)
+        setup(df.dropna(subset=chosen_target), target=chosen_target, session_id = 2774764,imputation_type = 'simple',numeric_imputation='mean',categorical_imputation='mode')
+        setup_df = pull()
+        st.dataframe(setup_df)
+        best_model = compare_models(n_select = 5)
+        compare_df = pull()
+        st.dataframe(compare_df)
+        plot_model(best_model, plot='residuals', display_format='streamlit')
+        plot_model(best_model, plot='feature', display_format='streamlit')
+        plot_model(best_model, plot='error', display_format='streamlit')
+        save_model(best_model, 'best_model')
+        # y = df[chosen_target]
+        # X = df.loc[:, df.columns!=chosen_target]
+        # X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=.5,random_state =65481254)
+        # reg = LazyRegressor(verbose=0,ignore_warnings=False, custom_metric=None )
+        # models,predictions = reg.fit(X_train, X_test, y_train, y_test)
+        # st.dataframe(models)
+        # model_dictionary = reg.provide_models(X_train,X_test,y_train,y_test)
+
+if choice == "Download": 
+    print("Working")
+    with open('best_model.pkl', 'rb') as f: 
+        st.download_button('Download Model', f, file_name="best_model.pkl")

dataset.csv

@@ -0,0 +1,63 @@
+Fruit,Form,RetailPrice,RetailPriceUnit,Yield,CupEquivalentSize,CupEquivalentUnit,CupEquivalentPrice
+Apples,Fresh,1.5193,per pound,0.9,0.2425,pounds,0.4094
+"Apples, applesauce",Canned,1.066,per pound,1,0.5401,pounds,0.5758
+"Apples, ready-to-drink",Juice,0.7804,per pint,1,8,fluid ounces,0.3902
+"Apples, frozen concentrate",Juice,0.5853,per pint,1,8,fluid ounces,0.2926
+Apricots,Fresh,2.9665,per pound,0.93,0.3638,pounds,1.1603
+"Apricots, packed in juice",Canned,1.6905,per pound,1,0.5401,pounds,0.9131
+"Apricots, packed in syrup or water",Canned,2.06,per pound,0.65,0.4409,pounds,1.3974
+Apricots,Dried,6.6188,per pound,1,0.1433,pounds,0.9485
+Bananas,Fresh,0.5249,per pound,0.64,0.3307,pounds,0.2712
+"Berries, mixed",Frozen,3.5585,per pound,1,0.3307,pounds,1.1768
+Blackberries,Fresh,6.0172,per pound,0.96,0.3197,pounds,2.0037
+Blackberries,Frozen,3.6362,per pound,1,0.3307,pounds,1.2025
+Blueberries,Fresh,4.1739,per pound,0.95,0.3197,pounds,1.4045
+Blueberries,Frozen,3.3898,per pound,1,0.3307,pounds,1.121
+Cantaloupe,Fresh,0.5767,per pound,0.51,0.3748,pounds,0.4238
+Cherries,Fresh,3.4269,per pound,0.92,0.3417,pounds,1.2729
+"Cherries, packed in syrup or water",Canned,4.5257,per pound,0.65,0.4409,pounds,3.07
+Clementines,Fresh,1.3847,per pound,0.77,0.463,pounds,0.8326
+Cranberries,Dried,4.6513,per pound,1,0.1232,pounds,0.5729
+Dates,Dried,5.5713,per pound,1,0.1653,pounds,0.9212
+Figs,Dried,6.8371,per pound,0.96,0.1653,pounds,1.1776
+"Fruit cocktail, packed in juice",Canned,1.7198,per pound,1,0.5401,pounds,0.9289
+"Fruit cocktail, packed in syrup or water",Canned,1.5932,per pound,0.65,0.4409,pounds,1.0808
+Grapefruit,Fresh,1.1695,per pound,0.49,0.463,pounds,1.105
+"Grapefruit, ready-to-drink",Juice,1.0415,per pint,1,8,fluid ounces,0.5208
+Grapes,Fresh,1.8398,per pound,0.96,0.3307,pounds,0.6338
+Grapes (raisins),Dried,3.7801,per pound,1,0.1653,pounds,0.625
+"Grapes, ready-to-drink",Juice,0.9215,per pint,1,8,fluid ounces,0.4607
+"Grapes, frozen concentrate",Juice,0.7119,per pint,1,8,fluid ounces,0.3559
+Honeydew,Fresh,0.9056,per pound,0.46,0.3748,pounds,0.7378
+Kiwi,Fresh,2.1849,per pound,0.76,0.3858,pounds,1.1091
+Mangoes,Fresh,1.1513,per pound,0.71,0.3638,pounds,0.5898
+Mangoes,Dried,10.5527,per pound,1,0.1253,pounds,1.3219
+Nectarines,Fresh,1.9062,per pound,0.91,0.3197,pounds,0.6696
+Oranges,Fresh,1.2131,per pound,0.68,0.4079,pounds,0.7276
+"Oranges, ready-to-drink",Juice,0.9842,per pint,1,8,fluid ounces,0.4921
+"Oranges, frozen concentrate",Juice,0.769,per pint,1,8,fluid ounces,0.3845
+Papaya,Fresh,1.2904,per pound,0.62,0.3086,pounds,0.6424
+Papaya,Dried,5.5089,per pound,1,0.1543,pounds,0.8502
+Peaches,Fresh,1.7167,per pound,0.96,0.3417,pounds,0.6111
+"Peaches, packed in juice",Canned,2.0237,per pound,1,0.5401,pounds,1.0931
+"Peaches, packed in syrup or water",Canned,1.8117,per pound,0.65,0.4409,pounds,1.229
+Peaches,Frozen,3.3867,per pound,1,0.3307,pounds,1.12
+Pears,Fresh,1.5865,per pound,0.9,0.3638,pounds,0.6412
+"Pears, packed in juice",Canned,1.9546,per pound,1,0.5401,pounds,1.0557
+"Pears, packed in syrup or water",Canned,1.897,per pound,0.65,0.4409,pounds,1.2868
+Pineapple,Fresh,0.5685,per pound,0.51,0.3638,pounds,0.4055
+"Pineapple, packed in juice",Canned,1.4344,per pound,1,0.5401,pounds,0.7748
+"Pineapple, packed in syrup or water",Canned,1.4067,per pound,0.65,0.4409,pounds,0.9543
+Pineapple,Dried,6.6492,per pound,1,0.1543,pounds,1.0261
+"Pineapple, ready-to-drink",Juice,1.0288,per pint,1,8,fluid ounces,0.5144
+"Pineapple, frozen concentrate",Juice,0.6973,per pint,1,8,fluid ounces,0.3486
+Plum,Fresh,2.0292,per pound,0.94,0.3638,pounds,0.7852
+Plum (prunes),Dried,5.7042,per pound,1,0.1874,pounds,1.0689
+"Plum (prune), ready-to-drink",Juice,1.5522,per pint,1,8,fluid ounces,0.7761
+Pomegranate,Fresh,2.235,per pound,0.56,0.3417,pounds,1.3638
+"Pomegranate, ready-to-drink",Juice,3.122,per pint,1,8,fluid ounces,1.561
+Raspberries,Fresh,6.6391,per pound,0.96,0.3197,pounds,2.2107
+Raspberries,Frozen,4.1877,per pound,1,0.3307,pounds,1.3849
+Strawberries,Fresh,2.58,per pound,0.94,0.3197,pounds,0.8774
+Strawberries,Frozen,2.8189,per pound,1,0.3307,pounds,0.9322
+Watermelon,Fresh,0.3604,per pound,0.52,0.3307,pounds,0.2292

requirements.txt

@@ -0,0 +1,157 @@
+# alembic==1.8.1
+# altair==4.2.0
+# asttokens==2.0.8
+# attrs==22.1.0
+# backcall==0.2.0
+# blinker==1.5
+# blis==0.7.9
+# Boruta==0.3
+# cachetools==5.2.0
+# catalogue==1.0.2
+# certifi==2022.9.24
+# charset-normalizer==2.1.1
+# click==8.1.3
+# cloudpickle==2.2.0
+# colorama==0.4.6
+# colorlover==0.3.0
+# commonmark==0.9.1
+# cufflinks==0.17.3
+# cycler==0.11.0
+# cymem==2.0.7
+# databricks-cli==0.17.3
+# debugpy==1.6.3
+django
+# decorator==5.1.1
+# docker==6.0.0
+# entrypoints==0.4
+# executing==1.1.1
+# Flask==2.2.2
+# fonttools==4.38.0
+# funcy==1.17
+# future==0.18.2
+# gensim==3.8.3
+# gitdb==4.0.9
+# GitPython==3.1.29
+# greenlet==1.1.3.post0
+# htmlmin==0.1.12
+# idna==3.4
+# ImageHash==4.3.1
+# imbalanced-learn==0.7.0
+# importlib-metadata==5.0.0
+# ipykernel==6.16.2
+ipython
+# ipywidgets==8.0.2
+# itsdangerous==2.1.2
+# jedi==0.18.1
+# Jinja2==3.1.2
+# joblib==1.2.0
+# jsonschema==4.16.0
+# jupyter_client==7.4.4
+# jupyter_core==4.11.2
+# jupyterlab-widgets==3.0.3
+# kiwisolver==1.4.4
+# kmodes==0.12.2
+# lightgbm==3.3.3
+# llvmlite==0.37.0
+lazypredict
+# Mako==1.2.3
+# MarkupSafe==2.1.1
+matplotlib
+matplotlib-inline
+# missingno==0.5.1
+# mlflow==1.30.0
+# mlxtend==0.19.0
+# multimethod==1.9
+# murmurhash==1.0.9
+# nest-asyncio==1.5.6
+# networkx==2.8.7
+# nltk==3.7
+# numba==0.54.1
+# numexpr==2.8.3
+numpy
+# oauthlib==3.2.2
+# packaging==21.3
+pandas
+pandas-profiling
+# parso==0.8.3
+# patsy==0.5.3
+# phik==0.12.2
+# pickleshare==0.7.5
+# pickle5
+# Pillow==9.2.0
+# plac==1.1.3
+plotly
+# preshed==3.0.8
+# prometheus-client==0.15.0
+# prometheus-flask-exporter==0.20.3
+# prompt-toolkit==3.0.31
+# protobuf==3.20.3
+# psutil==5.9.3
+# pure-eval==0.2.2
+# pyarrow==9.0.0
+pycaret[full]
+# pydantic==1.10.2
+# pydeck==0.8.0b4
+# Pygments==2.13.0
+# PyJWT==2.6.0
+# pyLDAvis==3.3.1
+# Pympler==1.0.1
+# pynndescent==0.5.7
+# pyod==1.0.6
+# pyparsing==3.0.9
+# pyrsistent==0.18.1
+python-dateutil
+pytz
+# pytz-deprecation-shim==0.1.0.post0
+# pywin32==304
+# PyYAML==5.4.1
+# pyzmq==24.0.1
+# querystring-parser==1.2.4
+# regex==2022.9.13
+requests
+# rich==12.6.0
+scikit-learn
+scikit-plot
+scipy
+# seaborn
+# semver==2.13.0
+# six==1.16.0
+# sklearn
+# smart-open==6.2.0
+# smmap==5.0.0
+# spacy==2.3.8
+# SQLAlchemy==1.4.42
+# sqlparse==0.4.3
+# srsly==1.0.6
+# stack-data==0.5.1
+statsmodels
+streamlit
+streamlit-pandas-profiling
+# tabulate==0.9.0
+# tangled-up-in-unicode==0.2.0
+# tenacity==8.1.0
+# textblob==0.17.1
+# thinc==7.4.6
+# threadpoolctl==3.1.0
+# toml==0.10.2
+# toolz==0.12.0
+# tornado==6.2
+# tqdm==4.64.1
+# traitlets==5.5.0
+# typing_extensions==4.4.0
+# tzdata==2022.5
+# tzlocal==4.2
+# umap-learn==0.5.3
+# urllib3==1.26.12
+# validators==0.20.0
+# visions==0.7.5
+# waitress==2.1.2
+# wasabi==0.10.1
+# watchdog==2.1.9
+# wcwidth==0.2.5
+# websocket-client==1.4.1
+# Werkzeug==2.2.2
+# widgetsnbextension==4.0.3
+# wordcloud==1.8.2.2
+# yellowbrick==1.2.1
+# zipp==3.10.0