Rodrigo Leite rodrigols89

🎯

Creating Things & Solving Problems

Creating Things and Solving Problems

rodrigols89 / percent_missing.py

Created September 18, 2020 20:54

	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)

rodrigols89 / isnull_sum.py

Created September 18, 2020 20:52

	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)

rodrigols89 / isnull.py

Created September 18, 2020 20:50

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

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

	print(isnull)

rodrigols89 / shape.py

Created September 18, 2020 20:47

	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))

rodrigols89 / dropna.py

Created September 18, 2020 20:45

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

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

	print(dt.head())

rodrigols89 / olympic_history.py

Created September 18, 2020 20:42

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

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

	print(data.head())
	print(data.dtypes)

rodrigols89 / astype.py

Created September 18, 2020 20:39

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

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

	data['DataYear'] = data['DataYear'].astype(object)
	print(data.dtypes)

rodrigols89 / dtypes_pandas.py

Created September 18, 2020 20:36

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

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

rodrigols89 / first_sample.py

Created September 18, 2020 20:34

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

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

rodrigols89 / pizza_predict-v2.py

Created September 15, 2020 05:59

	from sklearn.model_selection import train_test_split
	from sklearn.linear_model import LinearRegression
	from matplotlib import pyplot as plt

	diameterPassed = float(input("What's the diameter(cm) of the pizza you want? "))

	diameters = [[7], [10], [15], [30], [45], [13], [60], [100], [5], [30], [90], [18], [70], [110], [25]]
	prices = [[8], [11], [16], [38.5], [52], [14], [70], [90], [6], [38.5], [102], [20], [85], [100], [34]]

	model = LinearRegression()