From 6a292ad36495d10258fda288fd0ee94f8f80bd78 Mon Sep 17 00:00:00 2001
From: "annalyovushkina@yandex.ru" <annalyovushkina@yandex.ru>
Date: Fri, 29 Nov 2024 03:01:55 +0400
Subject: [PATCH] =?UTF-8?q?=D1=84=D0=B8=D0=BD=D0=B0=D0=BB=20=D1=82=D0=BE?=
 =?UTF-8?q?=D1=87=D0=BD=D0=BE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 lab_4/__pycache__/utils.cpython-312.pyc | Bin 2826 -> 0 bytes
 lab_4/utils.py                          |  79 ------------------------
 2 files changed, 79 deletions(-)
 delete mode 100644 lab_4/__pycache__/utils.cpython-312.pyc
 delete mode 100644 lab_4/utils.py

diff --git a/lab_4/__pycache__/utils.cpython-312.pyc b/lab_4/__pycache__/utils.cpython-312.pyc
deleted file mode 100644
index 8d965a85f693d9f63443297b54e49ad0ec6741b7..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 2826
zcma)8O>7fK6yEjP>$M&KBnX00RHg;e7#RZv8k!nV3IxKRfbi2sk*tk(94}e#nw@om
zqqP*F9wKqct*Jn2r1p>s4v|__tw1VLFO_<+>7mvNq)ME63nC{@eKX#59Jny{?##}-
z_vXFteQ$REiblg6w8YK9sb669l0JAX<PKhs!{8fE;S^ruO8hv_)3HzUjSJ8Vny=&^
z_p>>_7AT41BF}}|KP9LHFpvEkzk-+qdj+2&ejOMOR(&byKe|zhcLLWcWes0~QRtLx
z$s?v*!tju=Oj*@)7A97Xlr`0IL=#&TQ_qW3(QQHK1-M>^ebigqXA5)iX#441;im^V
z&g`~$cwkNOQ3=~$5az(jLwEizZ}T>H3oN|dW_UB!p)J__TY6kgv^krf;%RiXpcU{e
z*rFY@g9>l^<^W+k@W}trU7PTOq*M#l!nKGkD1qr6;NumGM#7ri_N!w~@_g->3wd)i
z*69I`BffJS#3ET<4!K(_&#qy&d+7Fd$PT}!WTYUD0j3l=y4PF;BIxRfHDpKN*Y!@6
z(ORq)uO&Kse&5)low0T3$2#XbW45Dq%nsXeJ3)O-iE=-{97fQ_D0v8y(PddzWP%hR
zS%H!ask&t#t7u}3NM({>kQ!jDOQRWCOCyj+lz%B^r(kHBF{|oR2(<H-YUr|tOc@3Q
zl}%$tRj`64t6&hL3c+R?%@(nV5tj2s*FI7SGeuw*OD(7y3b0=V6YvQ9BxRh3#XQOz
zTBW3ePes`R)$}G)MY&~*ZbxV|Cf2~{3<me`?F!cORb&*HHyg&OaLZ~cgGMb>#%94V
zO9aF`*C<*RjS@mJE4ogHZ<pdg3R$yi9%sTVoXawW)52!UqkZkhR+U0d)yowN4ZV{A
zwoY?2$^<qt19_Q*u&6JYPQ<D?@Ls3U4j}-st$z*TV$*KKE^-XGSyj`hHOPsAAX=)(
z(9hG{=^1pLRAf!7wvACNJnUzUiUwH)P(hKRr^%C8YxzWJkYmt*HwDd*EoOpE1LP3a
zJJXa+o2O~?)O(jmv#M1D-l#wsy4waKUK9)ym$~$S+@R`)|8x_onPHaQ?31Dw3cgb|
zF`;NcH88*1jD|7+&bLI{_DH3KARz}c2U>BPAY+tr#F8zV2dJVnx@71$jR2#oY;laP
zjp`tx=W*N64N7uq3h*q;%mZ40Z=Lf4DVJ7P*>S&#Q_K_)is_^gj37GJGh~O_Tb=TX
zoMuwD04T;|fYhybb||#snQ9$~YbWMXUS$)sr;v6pq!>syEF>!ms+3(M=63CYY9*}&
zk1SBVo066i9LXhH)d{uUWa=Dtx;haw>1!t?I$?&+Y11@JC)naIG3hJA5j3njzOrJ%
ziN>Y69m%UGC*fK5%EAe6kkXMnCOV<kEbzjlF9e7G(&4Mj4g=B&Qb=*B>;$VVXdMv-
zbfU*QRdQ_;j@W|T)gqP?sM0jFbcjW|VGBy@P3=uKKQwV2jzuyd>u_>T$ZBa~c=TfK
z^5~?p@6f^Ag{m=gofM~4T^`O1Pe7gJ4o_4pRU?^l)!EH>51jK3PB>F6qvb5!oP8&l
z2zHj>BIn@EKF_T|C-p3zZ3O$4s*T{l%E@QJ{m*0Dn_Yv=cyj6J@>liP{#ODYJ@8r(
z;^8$;2!+?eoV0!E&ObZ%H{j32>&fHwFRnI{V}Hl4)un6yN{RX5rj%%gl67gvE5R2M
z=ZDwB+}@$46k0gAczbzlWvH>|$kT~+!M9gz`1|M2E=(=XE{kgtCnXjS-mN{4_beX0
zSNlO&KKp(2XJPfsPhAa^eHPEwrEEQ(ZN_^a^nBO%ZQuP5R(e-Ie)7rh+268{kN^2;
zJ$|JwU0D;k9lMr`tI0<HP$T(y-M{Vmo+C{u-jrg^?%rn4?&j7H*CS#-Z2i&v$ikV$
z>q{f+39c)?aOd8!2Pc=M`xhUbTooUlZ}bg5+4bwx<8-5M<XL2-?jNZ~Mw*c=i#L{T
zE>EpgRtxn=w(ifq21vP7z}yPm)FIYho^S_$oN&vhe&SL}azv|IhDtN(H<=@r;V_Vi
z8G{E#UZ<B#Ygjh*OvzBNmLpih>`lsu&eHcIXMRY<cf#$Blm)qphL4;5@JPSb$Z5E(
z2|Ulg;I_Zyw!Gl_UT}vYY1@*`cuzCh-Hi1#ySKiIp5ggpYcWoYEPS@8E+<z;SF2A`
Q^~m`~;KF*GF0yU@2OB6GD*ylh

diff --git a/lab_4/utils.py b/lab_4/utils.py
deleted file mode 100644
index cb8c396..0000000
--- a/lab_4/utils.py
+++ /dev/null
@@ -1,79 +0,0 @@
-from typing import Tuple
-
-import pandas as pd
-from pandas import DataFrame
-from sklearn.model_selection import train_test_split
-
-
-def split_stratified_into_train_val_test(
-    df_input,
-    stratify_colname="y",
-    frac_train=0.6,
-    frac_val=0.15,
-    frac_test=0.25,
-    random_state=None,
-) -> Tuple[DataFrame, DataFrame, DataFrame, DataFrame, DataFrame, DataFrame]:
-    """
-    Splits a Pandas dataframe into three subsets (train, val, and test)
-    following fractional ratios provided by the user, where each subset is
-    stratified by the values in a specific column (that is, each subset has
-    the same relative frequency of the values in the column). It performs this
-    splitting by running train_test_split() twice.
-
-    Parameters
-    ----------
-    df_input : Pandas dataframe
-        Input dataframe to be split.
-    stratify_colname : str
-        The name of the column that will be used for stratification. Usually
-        this column would be for the label.
-    frac_train : float
-    frac_val   : float
-    frac_test  : float
-        The ratios with which the dataframe will be split into train, val, and
-        test data. The values should be expressed as float fractions and should
-        sum to 1.0.
-    random_state : int, None, or RandomStateInstance
-        Value to be passed to train_test_split().
-
-    Returns
-    -------
-    df_train, df_val, df_test :
-        Dataframes containing the three splits.
-    """
-
-    if frac_train + frac_val + frac_test != 1.0:
-        raise ValueError(
-            "fractions %f, %f, %f do not add up to 1.0"
-            % (frac_train, frac_val, frac_test)
-        )
-
-    if stratify_colname not in df_input.columns:
-        raise ValueError("%s is not a column in the dataframe" % (stratify_colname))
-
-    X = df_input  # Contains all columns.
-    y = df_input[
-        [stratify_colname]
-    ]  # Dataframe of just the column on which to stratify.
-
-    # Split original dataframe into train and temp dataframes.
-    df_train, df_temp, y_train, y_temp = train_test_split(
-        X, y, stratify=y, test_size=(1.0 - frac_train), random_state=random_state
-    )
-
-    if frac_val <= 0:
-        assert len(df_input) == len(df_train) + len(df_temp)
-        return df_train, pd.DataFrame(), df_temp, y_train, pd.DataFrame(), y_temp
-
-    # Split the temp dataframe into val and test dataframes.
-    relative_frac_test = frac_test / (frac_val + frac_test)
-    df_val, df_test, y_val, y_test = train_test_split(
-        df_temp,
-        y_temp,
-        stratify=y_temp,
-        test_size=relative_frac_test,
-        random_state=random_state,
-    )
-
-    assert len(df_input) == len(df_train) + len(df_val) + len(df_test)
-    return df_train, df_val, df_test, y_train, y_val, y_test