import numpy as np import pandas as pd from numpy.random import randn

np.random.seed(101)

df = pd.DataFrame(randn(5,4), ["a", "b", "c", "d", "e"], ["one", "two", "three", "four"]) df

randn(5,4)

# Call columns # df.one df[["one", "two"]]

# Create new coloum df["new_column"] = df["one"] + df["two"]

df

df.drop("new_column", axis=1)

df

#Para eliminarlo del df original. Inplace true df.drop("new_column", axis=1, inplace=True) df

df >= 0

df[df >= 0]

df["one"]>= 0

# Si quiero filtrar df[df["one"]>=0]

# Si negar una condición df[~(df["one"]>=0)]

df[(df["one"]>=0) & (df["four"]< 1)]

# Quitar los index df.reset_index()

index = ["a1", "a2", "a3", "a4", "a5"] df["index"] = index df.set_index("index")

# Index Levels outside = ['G1','G1','G1','G2','G2','G2'] inside = [1,2,3,1,2,3] hier_index = list(zip(outside,inside)) hier_index = pd.MultiIndex.from_tuples(hier_index)

type(hier_index)

hier_index

df = pd.DataFrame(np.random.randn(6,2),index=hier_index,columns=['A','B']) df

df.loc["G1", 1]

df.index.names df.index.names = ["Grupos", "numeros"]

df.index

df.xs(1, level="numeros")

df = pd.DataFrame(np.random.rand(5,4)) df[df <= 0.5] = np.nan df

df

# Retorna los row que tenga almenos 3 not-nan df.dropna(thresh=3)

df.fillna(0)

df.mean()

data = {'Company':['GOOG','GOOG','MSFT','MSFT','FB','FB'], 'Person':['Sam','Charlie','Amy','Vanessa','Carl','Sarah'], 'Sales':[200,120,340,124,243,350]} df = pd.DataFrame(data) df

df_company = df.groupby("Company") df_company.mean()

df_company.sum()

df_company.sample()

df.groupby("Company").sum().loc["FB"]

df.groupby("Company").count()

df.groupby("Company").describe().transpose()

df_books = pd.read_csv("/work/bestsellers-with-categories_e591527f-ae45-4fa5-b0d1-d50142128fa6.csv") df_books

df_books.groupby("Author").sum()

df_books.groupby("Author").agg(["min", "max"])

df_books.groupby("Author").agg({"Year": "mean", "User Rating": "min"})

df_books.groupby('Author').agg({"Year": lambda x: x.mean() - 2000})

url = "https://static.platzi.com/media/public/uploads/hpcharactersdataraw_3d934e85-dfa4-42ec-8520-fadfbecae574.json" pd.read_json(url)

left = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'], 'A': ['A0', 'A1', 'A2', 'A3'], 'B': ['B0', 'B1', 'B2', 'B3']}) right = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'], 'C': ['C0', 'C1', 'C2', 'C3'], 'D': ['D0', 'D1', 'D2', 'D3']}) print(left, "\n\n", right)

pd.merge(left, right, how="inner", on="key")

left = pd.DataFrame({ 'A': ['A0', 'A1', 'A2', 'A3'], 'B': ['B0', 'B1', 'B2', 'B3']}, index = ['K0', 'K1', 'K2', 'K3']) right = pd.DataFrame({ 'C': ['C0', 'C1', 'C2', 'C3'], 'D': ['D0', 'D1', 'D2', 'D3']}, index = ['K0', 'K1', 'K2', 'K3']) print(left, "\n\n", right)

left.join(right)

df = pd.DataFrame({'col1':[1,2,3,4],'col2':[444,555,666,444],'col3':['abc','def','ghi','xyz']}) df.head()

df["col2"].unique()

# Si quiero la cuenta de los unicos df["col2"].nunique()

# Retorna el numero de ocurencias de cada label df["col2"].value_counts()

df

df["col2"].apply(lambda x: x*2)

df.drop("col1", axis=1)

#sort by columns df.sort_values('col2')

data = {'A':['foo','foo','foo','bar','bar','bar'], 'B':['one','one','two','two','one','one'], 'C':['x','y','x','y','x','y'], 'D':[1,3,2,5,4,1]} df = pd.DataFrame(data) df

df.pivot_table(values="D", columns="A").T

df.pivot_table(values="D", index=["A", "B"], columns="C").T