mooksys / 2020-Deep-Learning-Study

Deep Learning Teacher Group Study
0 stars 0 forks source link

2020.10.09 Study Memo #1

Open mooksys opened 3 years ago

mooksys commented 3 years ago

2020.10.09 Study Memo

https://nipa.elice.io/

Open kakao https://open.kakao.com/o/gcTXx9wc

mooksys commented 3 years ago

`##### import numpy

def main(): (N, X, Y) = read_data() print(N) print(X) print(Y)

def read_data():

Implement here

N = int(input())
X = []
Y = []
for i in range(N):
    line = input().strip().split(" ")
    X.append(float(line[0]))
    Y.append(float(line[1]))
return (N, X, Y)

if name == "main": main()`

`#####

import numpy import statsmodels.api from draw_graph import visualize

def main(): (N, X, Y) = read_data() results = do_simple_regression(N, X, Y)

visualize(X, Y, results)

def read_data():

1

# Copy-and-paste your code from the previous exercise
N = int(input())
X = []
Y = []
for i in range(N):
    line = input().strip().split(" ")
    X.append(float(line[0]))
    Y.append(float(line[1]))
return (N, X, Y)

def do_simple_regression(N, X, Y):

2

X = statsmodels.api.add_constant(X)
results = statsmodels.api.OLS(Y, X).fit()
return results

if name == "main": main()`

mooksys commented 3 years ago

import statsmodels.api as stapi import numpy import pandas as pd

def main(): (N, X, Y) = read_data()

results = do_multivariate_regression(N, X, Y)
print(results.summary())

effective_variables = get_effective_variables(results)
print(effective_variables)

def do_multivariate_regression(N, X, Y):

2

X = numpy.array(X)
results = stapi.OLS(Y,X).fit()
print(results)
return results

def get_effective_variables(results): eff_vars = []

3

n = 0
df_result = pd.DataFrame(results.summary().tables[1].data[1:])  
for pvalue in df_result[4]:
    if float(pvalue) < 0.05:
        eff_vars.append(df_result.loc[0][n])
    n+=1
return eff_vars

def read_data():

1

N = 0
X = []
Y = []
with open("students.txt") as f:
    next(f)
    for line in f:
        splits = line.strip().split(" ")
        numeric_data = [float(x) for x in splits]
        x = numeric_data[0:-1]
        y = numeric_data[-1]
        X.append(x)
        Y.append(y)
        N += 1

# X must be numpy.array in (30 * 5) shape.
# Y must be 1-dimensional numpy.array.
X = numpy.array(X)
Y = numpy.array(Y)
return (N, X, Y)

if name == "main": main()