app.py

import streamlit as st
from data_utils import *
import xarray as xr
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import pickle
import glob, os
import re
import tensorflow as tf
import netCDF4
import copy
import string
import h5py
from tqdm import tqdm


st.title('A _Quickstart Notebook_ for :blue[ClimSim]:')
st.link_button("ClimSim", "https://huggingface.co/datasets/LEAP/subsampled_low_res/tree/main",use_container_width=True)
st.header('**Step 1:**  Import data_utils')
st.code('''from data_utils import *''',language='python')

st.header('**Step 2:**  Instantiate class')
st.code('''#Change the path to your own
grid_info = xr.open_dataset('ClimSim_low-res_grid-info.nc')
input_mean = xr.open_dataset('input_mean.nc')
input_max = xr.open_dataset('input_max.nc')
input_min = xr.open_dataset('input_min.nc')
output_scale = xr.open_dataset('output_scale.nc')

data = data_utils(grid_info = grid_info,
                  input_mean = input_mean,
                  input_max = input_max,
                  input_min = input_min,
                  output_scale = output_scale)
data.set_to_v1_vars()''',language='python')

#Change the path to your own
grid_info = xr.open_dataset('ClimSim_low-res_grid-info.nc')
input_mean = xr.open_dataset('input_mean.nc')
input_max = xr.open_dataset('input_max.nc')
input_min = xr.open_dataset('input_min.nc')
output_scale = xr.open_dataset('output_scale.nc')

data = data_utils(grid_info = grid_info,
                  input_mean = input_mean,
                  input_max = input_max,
                  input_min = input_min,
                  output_scale = output_scale)

data.set_to_v1_vars()


st.header('**Step 3:**  Load training and validation data')
st.code('''data.input_train = data.load_npy_file('train_input_small.npy')
data.target_train = data.load_npy_file('train_target_small.npy')
data.input_val = data.load_npy_file('val_input_small.npy')
data.target_val = data.load_npy_file('val_target_small.npy')''',language='python')

data.input_train = data.load_npy_file('train_input_small.npy')
data.target_train = data.load_npy_file('train_target_small.npy')
data.input_val = data.load_npy_file('val_input_small.npy')
data.target_val = data.load_npy_file('val_target_small.npy')


st.header('**Step 4:**  Train models')
st.subheader('Train constant prediction model')
st.code('''const_model = data.target_train.mean(axis = 0)''',language='python')

const_model = data.target_train.mean(axis = 0)


st.subheader('Train multiple linear regression model')
st.text('adding bias unit')
st.code('''X = data.input_train
bias_vector = np.ones((X.shape[0], 1))
X = np.concatenate((X, bias_vector), axis=1)''',language='python')

X = data.input_train
bias_vector = np.ones((X.shape[0], 1))
X = np.concatenate((X, bias_vector), axis=1)


st.text('create model')
st.code('''mlr_weights = np.linalg.inv(X.transpose()@X)@X.transpose()@data.target_train''',language='python')

mlr_weights = np.linalg.inv(X.transpose()@X)@X.transpose()@data.target_train


st.subheader('Train your models here')
st.code('''### 
# train your model here
###''',language='python')

### 
# train your model here
###


st.link_button("Go to Original Dataset", "https://huggingface.co/datasets/LEAP/subsampled_low_res/tree/main",use_container_width=True)

st.header('**Step 5:**  Evaluate on validation data')















data.set_pressure_grid(data_split = 'val')

# Constant Prediction
const_pred_val = np.repeat(const_model[np.newaxis, :], data.target_val.shape[0], axis = 0)
print(const_pred_val.shape)

# Multiple Linear Regression
X_val = data.input_val
bias_vector_val = np.ones((X_val.shape[0], 1))
X_val = np.concatenate((X_val, bias_vector_val), axis=1)

mlr_pred_val = X_val@mlr_weights
print(mlr_pred_val.shape)

# Load your prediction here

# Load predictions into data_utils object
data.model_names = ['const', 'mlr'] # add names of your models here
preds = [const_pred_val, mlr_pred_val] # add your custom predictions here
data.preds_val = dict(zip(data.model_names, preds))

data.reweight_target(data_split = 'val')
data.reweight_preds(data_split = 'val')
data.metrics_names = ['MAE', 'RMSE', 'R2', 'bias']
data.create_metrics_df(data_split = 'val')

letters = string.ascii_lowercase

# create custom dictionary for plotting
dict_var = data.metrics_var_val
plot_df_byvar = {}
for metric in data.metrics_names:
    plot_df_byvar[metric] = pd.DataFrame([dict_var[model][metric] for model in data.model_names],
                                               index=data.model_names)
    plot_df_byvar[metric] = plot_df_byvar[metric].rename(columns = data.var_short_names).transpose()

# plot figure
fig, axes = plt.subplots(nrows  = len(data.metrics_names), sharex = True)
for i in range(len(data.metrics_names)):
    plot_df_byvar[data.metrics_names[i]].plot.bar(
        legend = False,
        ax = axes[i])
    if data.metrics_names[i] != 'R2':
        axes[i].set_ylabel('$W/m^2$')
    else:
        axes[i].set_ylim(0,1)
    axes[i].set_title(f'({letters[i]}) {data.metrics_names[i]}')

    
    
axes[i].set_xlabel('Output variable')
axes[i].set_xticklabels(plot_df_byvar[data.metrics_names[i]].index, \
    rotation=0, ha='center')

axes[0].legend(columnspacing = .9,
               labelspacing = .3,
               handleheight = .07,
               handlelength = 1.5,
               handletextpad = .2,
               borderpad = .2,
               ncol = 3,
               loc = 'upper right')
fig.set_size_inches(7,8)
fig.tight_layout()
st.pyplot(fig)

# path to target input
data.input_scoring = np.load('scoring_input_small.npy')
# path to target output
data.target_scoring = np.load('scoring_target_small.npy')
data.set_pressure_grid(data_split = 'scoring')
# constant prediction
const_pred_scoring = np.repeat(const_model[np.newaxis, :], data.target_scoring.shape[0], axis = 0)
print(const_pred_scoring.shape)

# multiple linear regression
X_scoring = data.input_scoring
bias_vector_scoring = np.ones((X_scoring.shape[0], 1))
X_scoring = np.concatenate((X_scoring, bias_vector_scoring), axis=1)
mlr_pred_scoring = X_scoring@mlr_weights
print(mlr_pred_scoring.shape)

# Your model prediction here

# Load predictions into object
data.model_names = ['const', 'mlr'] # model name here
preds = [const_pred_scoring, mlr_pred_scoring] # add prediction here
data.preds_scoring = dict(zip(data.model_names, preds))
# weight predictions and target
data.reweight_target(data_split = 'scoring')
data.reweight_preds(data_split = 'scoring')

# set and calculate metrics
data.metrics_names = ['MAE', 'RMSE', 'R2', 'bias']
data.create_metrics_df(data_split = 'scoring')

# set plotting settings

letters = string.ascii_lowercase

# create custom dictionary for plotting
dict_var = data.metrics_var_scoring
plot_df_byvar = {}
for metric in data.metrics_names:
    plot_df_byvar[metric] = pd.DataFrame([dict_var[model][metric] for model in data.model_names],
                                               index=data.model_names)
    plot_df_byvar[metric] = plot_df_byvar[metric].rename(columns = data.var_short_names).transpose()

# plot figure
fig, axes = plt.subplots(nrows  = len(data.metrics_names), sharex = True)
for i in range(len(data.metrics_names)):
    plot_df_byvar[data.metrics_names[i]].plot.bar(
        legend = False,
        ax = axes[i])
    if data.metrics_names[i] != 'R2':
        axes[i].set_ylabel('$W/m^2$')
    else:
        axes[i].set_ylim(0,1)

    axes[i].set_title(f'({letters[i]}) {data.metrics_names[i]}')
axes[i].set_xlabel('Output variable')
axes[i].set_xticklabels(plot_df_byvar[data.metrics_names[i]].index, \
    rotation=0, ha='center')

axes[0].legend(columnspacing = .9,
               labelspacing = .3,
               handleheight = .07,
               handlelength = 1.5,
               handletextpad = .2,
               borderpad = .2,
               ncol = 3,
               loc = 'upper right')
fig.set_size_inches(7,8)
fig.tight_layout()
st.pyplot(fig)

st.markdown('Streamlit p')