nickinack

import numpy as np
import matplotlib.pyplot as plt
import random 
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression
from sklearn import metrics

nickinack

df1 = pd.read_csv("communities.data" , header=None)
def read_header(filename):
    '''
    Given a filename containing headers, extract the headers and assign it to df
    '''

    header_list = []
    with open(filename) as f:
        for line in f:
            if "@attribute" in line:

nickinack

def drop_columns(columns , df):
    '''
    Given dataframe , returns updated df with removed colums
    '''
    for i in columns:
        df = df.drop(i , axis=1)

    return df

drop_list = ['state' , 'county' , 'community' , 'communityname' , 'fold' ]

nickinack

x = df1.drop("ViolentCrimesPerPop", axis=1)
y = df1["ViolentCrimesPerPop"]
x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.8, random_state=24)
print(x_train.shape , y_train.shape)
print(x_test.shape , y_test.shape)

nickinack

def fitness_func(chromosome):
    columns = []
    for i in range(len(x_train.columns)):
        if i in chromosome:
            columns.append(x_train.columns[i])
    dist.append(columns)
    training_set = x_train[columns]
    print(training_set)
    test_set = x_test[columns]
    lg = LinearRegression().fit(training_set.values, y_train.values)

nickinack

class FeatureSolver(AbstractSolver):
    def __init__(
        self,
        problem_type=float,
        fitness_func= lambda a : fitness_func(a),
        pop_cnt: int = 40,
        gene_size: int = 50,
        max_gen: int = 2,
        mutation_ratio: float = 0.2,
        selection_ratio: float = 0.2,

nickinack

nickinack

nickinack

nickinack