world-ecoregion/utils.py

import numpy as np
import tensorflow as tf
import pandas as pd
from collections import Counter
from sklearn.utils import class_weight
from constants import *
import logging
import os

logger = logging.getLogger('main')
logger.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))


def normalize(v, o=None):
    if o is None:
        o = v
    return (v - np.mean(o)) / np.std(o)

def normalize_ndarray(ar, o=None):
    if o is None:
        o = ar

    # transpose: operate over columns
    tr = np.transpose(ar)
    to = np.transpose(o)
    for i in range(tr.shape[0]):
        tr[i] = normalize(tr[i], to[i])

    # transpose back
    return np.transpose(tr)

def dataframe_to_dataset_biomes(df):
    rows = df.shape[0]

    # 8 for seasonal temp and precipitation
    # 3 for latitude, elevation and distance_to_water
    input_columns = 11 

    tf_inputs = np.empty((0, input_columns))
    tf_output = np.empty((0))

    for year in range(MIN_YEAR, MAX_YEAR + 1):
        local_inputs = list(INPUTS)
        for season in SEASONS:
            local_inputs += [
                'temp_{}_{}'.format(season, year),
                'precip_{}_{}'.format(season, year)
            ]


        local_df = df[local_inputs]

        tf_inputs = np.concatenate((tf_inputs, local_df.values), axis=0)
        tf_output = np.concatenate((tf_output, df[OUTPUT].values), axis=0)

    # balance class weights for the loss function, since the data is highly unbalanced
    num_classes = len(np.unique(tf_output))
    class_weights = class_weight.compute_class_weight('balanced', np.unique(tf_output), tf_output)
    logger.debug('class_weights %s', class_weights)

    tf_inputs = tf.cast(normalize_ndarray(tf_inputs), tf.float32)
    tf_output = tf.cast(tf_output, tf.int64)

    logger.debug('dataset size: rows=%d, input_columns=%d, num_classes=%d', int(tf_inputs.shape[0]), input_columns, num_classes)
    return int(tf_inputs.shape[0]), input_columns, num_classes, class_weights, tf.data.Dataset.from_tensor_slices((tf_inputs, tf_output))

def dataframe_to_dataset_temp_precip(df):
    rows = df.shape[0]

    # elevation, distance_to_water, latitude
    # season, year
    input_columns = 5
    num_classes = 2

    tf_inputs = np.empty((0, input_columns))
    tf_output = np.empty((0, num_classes))

    for year in range(MIN_YEAR, MAX_YEAR + 1):
        local_inputs = list(INPUTS)

        for idx, season in enumerate(SEASONS):
            season_index = idx / len(season)
            local_df = df[local_inputs]
            local_df.loc[:, 'season'] = pd.Series(np.repeat(season_index, rows), index=local_df.index)
            local_df.loc[:, 'year'] = pd.Series(np.repeat(year, rows), index=local_df.index)

            output = ['temp_{}_{}'.format(season, year), 'precip_{}_{}'.format(season, year)]
            tf_inputs = np.concatenate((tf_inputs, local_df.values), axis=0)
            tf_output = np.concatenate((tf_output, df[output].values), axis=0)

    tf_inputs = tf.cast(normalize_ndarray(tf_inputs), tf.float32)
    tf_output = tf.cast(tf_output, tf.float32)

    logger.debug('dataset size: rows=%d, input_columns=%d, num_classes=%d', int(tf_inputs.shape[0]), input_columns, num_classes)
    return int(tf_inputs.shape[0]), input_columns, num_classes, tf.data.Dataset.from_tensor_slices((tf_inputs, tf_output))


flatten = lambda l: [item for sublist in l for item in sublist]

def chunker(seq, size):
    return (seq[pos:pos + size] for pos in range(0, len(seq), size))