ID_correlation_measure.py

import numpy as np
import experiments_logging as log
import pandas as pd
import interaction_distance as id
import data_generator as dg

def evidence_ID():
    # no interaction
    b = np.matrix(np.random.uniform(1, 2, (4000, 1)))
    back = np.matrix(np.random.uniform(0, 2, (4000, 1)))
    res = np.append(b, back, axis=0)
    b1 = np.matrix(np.random.uniform(0, 2, (8000, 1)))

    # either horizontal or vertical tube
    # all = np.append(b1, res, axis=1)
    all = np.append(res, b1, axis=1)
    df = pd.DataFrame(all)
    df = df.sort_values(by=0).reset_index(drop=True)
    print(id.compute_ID(df.loc[:100, 1].to_frame(), df.loc[7900:8000, 1].to_frame(), [0, 2]))
    # log.plot_data_2d(df)
    # log.plot_data_2d(pd.concat([df.loc[:100], df.loc[7900:8000]], axis=0))

    # cube interaction
    b = np.matrix(np.random.uniform(1, 2, (4000, 1)))
    back = np.matrix(np.random.uniform(0, 2, (4000, 1)))
    res = np.append(b, back, axis=0)
    b1 = np.matrix(np.random.uniform(1, 2, (4000, 1)))
    back1 = np.matrix(np.random.uniform(0, 2, (4000, 1)))
    res1 = np.append(b1, back1, axis=0)

    all = np.append(res, res1, axis=1)
    df = pd.DataFrame(all)
    df = df.sort_values(by=0).reset_index(drop=True)
    print(id.compute_ID(df.loc[:100, 1].to_frame(), df.loc[7900:8000, 1].to_frame(), [0, 2]))
    # log.plot_data_2d(df)
    # log.plot_data_2d(pd.concat([df.loc[:100], df.loc[7900:8000]], axis=0))

cg = dg.produce_cube_generator(7, 0, 2, "i", ".csv")
data, filname = cg.build()
print(cg.subspaces)
print(cg.perf_disc)

data = pd.DataFrame(data)
dim_count = data.shape[1]
for curr in data[:-1]:
    dims = data.columns.tolist()
    dims.remove(curr)
    dims.remove(dim_count - 1)
    curr_data = data.sort_values(by=curr).reset_index(drop=True).loc[:, dims]
    rows = curr_data.shape[0]
    print('curr dimension', curr)
    for dim in dims:
        counter = 0
        ids = []
        while(True):
            if counter + 280 > rows:
                break
            ids.append(id.compute_ID(curr_data.loc[counter:counter + 140, dim].to_frame(),
                                     curr_data.loc[counter + 140: counter + 280, dim].to_frame(), [2] * dim_count))
            counter += 1
        # needs data normalization todo
        print('interaction with', dim, np.average(ids))
    # break