def complete_build(x_train, x_test, y_train, y_test):
#Called function post label encoding
lab_stats = create_stats(x_train,
x_test,
y_train,
y_test,
enc='labelencoder')
#Prepare data for one hot encoding
x_train, x_test, y_train, y_test = split_dataset(df)
category_index = [
x for x in range(len(df.columns))
if df[df.columns[x]].dtype == 'object'
]
#one hot encoding
x_train, x_test = ohe_encode(x_train, x_test, category_index)
#Called function post one hot encoding
ohe_stats = create_stats(x_train,
x_test,
y_train,
y_test,
enc='oheencoder')
final_stats = pd.concat([lab_stats, ohe_stats], axis=0)
final_stats = final_stats[['c_val', 'rmse', 'mae', 'r2']]
return final_stats
def plot_corr(df, size=11):
x_train, x_test, y_train, y_test = split_dataset(df)
df_train = pd.concat([x_train, y_train], axis=1)
corr = df_train.corr()
fig, ax = subplots(figsize=(size, size))
plt.set_cmap('YlOrRd')
ax.matshow(corr)
xticks(range(len(corr.columns)), corr.columns, rotation=90)
yticks(range(len(corr.columns)), corr.columns)
fig.savefig('./images/data_image.png')
return ax
# -*- coding: utf-8 -*-
from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
import matplotlib.pyplot as plt
from pandas.plotting import scatter_matrix
data = load_data('data/student-mat.csv')
x_train, x_test, y_train, y_test = split_dataset(data)
x_train, x_test = label_encode(x_train, x_test)
def visualise_data(data, figname):
plt.figure()
scatter_matrix(data, alpha=0.2, figsize=(15, 15), diagonal='kde')
#plt.savefig(figname)
plt.show()
# %load q03_ohe_encoder/build.py
from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import LabelEncoder
import pandas as pd
path = 'data/student-mat.csv'
df = load_data(path)
category_index = [
x for x in range(len(df.columns)) if df[df.columns[x]].dtype == 'object'
]
columns = [col for col in (df.columns) if df[col].dtype == 'object']
#print(df.shape)
print(category_index)
df_new = pd.get_dummies(df, columns=columns)
X_train, X_test, y_train, y_test = split_dataset(df_new)
def ohe_encode(X_train, X_test, defaults=category_index):
X_transform, X_test_transform = label_encode(X_train, X_test)
return X_transform, X_test_transform
ohe_encode(X_train, X_test, category_index)
def visualise_data(data, figname):
x_train, x_test, y_train, y_test = split_dataset(data)
plt = scatter_matrix(data, alpha=0.2)
#plt.show()
#plt.figtext = figname
return plt
