new folder who dis

This commit is contained in:
LinlyBoi
2023-03-31 13:13:55 +02:00
parent f49277bb06
commit 7ccdd5eb9a
5 changed files with 9 additions and 4 deletions

View File

@@ -1,7 +1,7 @@
# Getting and combining data # Getting and combining data
import pandas as pd import pandas as pd
import numpy as np import numpy as np
import scout from dwarves import scout
from numpy import ndarray from numpy import ndarray
from scipy.stats import binned_statistic from scipy.stats import binned_statistic
@@ -40,13 +40,18 @@ def slam_dunk(dataset, column, labels):
x_data = np.arange(0, len(dataset)) x_data = np.arange(0, len(dataset))
y_data = dataset[column] y_data = dataset[column]
x_bins, bin_edges, misc = binned_statistic(y_data, x_data, statistic='median', bins=len(labels)) x_bins, bin_edges, misc = binned_statistic(
y_data, x_data, statistic="median", bins=len(labels)
)
bin_intervals = pd.IntervalIndex.from_arrays(bin_edges[:-1], bin_edges[1:]) bin_intervals = pd.IntervalIndex.from_arrays(bin_edges[:-1], bin_edges[1:])
dataset['bin_value'] = dataset[column].apply(lambda x: set_to_median(x, bin_intervals)) dataset["bin_value"] = dataset[column].apply(
lambda x: set_to_median(x, bin_intervals)
)
return dataset return dataset
def set_to_median(x, bin_intervals): def set_to_median(x, bin_intervals):
for interval in bin_intervals: for interval in bin_intervals:
if x in interval: if x in interval:
return interval.mid return interval.mid