drigols

The Checklist (Good practices for good programmers)

• Software Engineering:
  • Data Science/A.I Project management:
    • Data Science projects types (+steps)
    • CRoss Industry Standard Process for Data Mining (CRISP-DM)
    • Data Pipeline
• Software Development & Engineering:
  • Algorithms:
    • Design and Analysis of Algorithms

drigols

def ApplyesKFold(x_axis, y_axis):
  # Linear Models.
  from sklearn.linear_model import LinearRegression
  from sklearn.linear_model import ElasticNet
  from sklearn.linear_model import Ridge
  from sklearn.linear_model import Lasso

  # Cross-Validation models.
  from sklearn.model_selection import cross_val_score
  from sklearn.model_selection import KFold

drigols

import matplotlib.pyplot as plt
import pandas as pd

from sklearn.model_selection import cross_val_score # Cross Validation Function.
from sklearn.model_selection import KFold # KFold Class.
from sklearn.linear_model import LinearRegression # Linear Regression class.

df = pd.read_csv("../datasets/Admission_Predict.csv")

df.drop('Serial No.', axis = 1, inplace = True)

drigols

import pandas as pd
pd.set_option('display.max_columns', 42)

data = pd.read_csv('../datasets/2015-building-energy-benchmarking.csv')

# Exibe a média de cada coluna.
print((data.isnull().sum() / len(data['OSEBuildingID'])) * 100, '\n')

data['ENERGYSTARScore'] = data['ENERGYSTARScore'].fillna(data['ENERGYSTARScore'].median())

drigols

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
data['Height'] = data['Height'].fillna(data['Height'].mean())
data['Weight'] = data['Weight'].fillna(data['Weight'].mean())

print(data[['Height', 'Weight']].head(20))

drigols

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
data['Medal'] = data['Medal'].fillna('Nenhuma')

print(data['Medal'].head(10))

drigols

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
percentMissing = (data.isnull().sum() / len(data['ID'])) * 100

print(percentMissing)

drigols

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
isNullSum = data.isnull().sum()

print(isNullSum)

drigols

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
isnull = data.isnull()

print(isnull)

drigols

import pandas as pd
pd.set_option('display.max_columns', 18)

data = pd.read_csv('../datasets/athlete_events.csv')
dt = data.dropna()

print("Full sample: {0}".format(data.shape))
print("Sample without NaN: {0}".format(dt.shape))