Pandas

import pandas as pd
#pd.Series?

animales = ['Tigre', 'Oso', 'Alce']
pd.Series(animales)

animales = ['Tigre', 'Oso', None]
pd.Series(animales)

numbers = [1, 2, None]
pd.Series(numbers)

import numpy as np
np.nan == None

np.nan == np.nan

np.isnan(np.nan)

sports = {'Futbol': 'Ecuador',
          'Golf': 'Escocia',
          'Sumo': 'Japon',
          'Taekwondo': 'Corea del Sur'}
s = pd.Series(sports)
s

s.index

s = pd.Series(['Tigre', 'Oso', 'Alce'], index=['India', 'America', 'Canada'])
s

sports = {'Futbol': 'Ecuador',
          'Golf': 'Escocia',
          'Sumo': 'Japon',
          'Taekwondo': 'Corea del Sur'}
s = pd.Series(sports, index=['Golf', 'Sumo', 'Hockey'])
s

sports = {'Futbol': 'Ecuador',
          'Golf': 'Escocia',
          'Sumo': 'Japon',
          'Taekwondo': 'Corea del Sur'}
s = pd.Series(sports)
s

s.iloc[3]

s.loc['Golf']

s[3]

s['Golf']

sports = {99: 'Ecuador',
          100: 'Escocia',
          101: 'Japon',
          102: 'Corea del Sur'}
s = pd.Series(sports)

#  s[0] # no se hace la consulta

s = pd.Series([100.00, 120.00, 101.00, 3.00])
s

total = 0
for item in s:
    total+=item
print(total)

s = pd.Series([1, 2, 3])
s.loc['Animal'] = 'Bears' # agregamos un elemento a la serie
s

import numpy as np
import pandas as pd

t = np.arange(0,10,0.1)
x = np.sin(t)
y = np.cos(t)

df = pd.DataFrame({'Time':t, 'x':x,'y':y})

df.Time
df['Time']

data = df[['Time','x']]

data.head()
data.tail()

data[4:10]

df[['Time','y']][4:10]

df.iloc[4:10,[0,2]]

# df.values

import pandas as pd
import numpy as np

data = pd.DataFrame({
    'Gender' : ['f', 'f', 'm', 'f', 'm','m', 'f', 'm', 'f', 'm', 'm'], 
    'TV': [3.4, 3.5, 2.6, 4.7, 4.1, 4.1, 5.1, 3.9, 3.7, 2.1, 4.3]
})

data

#Agrupamos los datos

grouped = data.groupby('Gender')
grouped.apply(print)

# Algunas estadísticas generales
grouped.describe()

# Graficamos los datos
grouped.plot()

# Separamos los grupos como DataFrames
df_female = grouped.get_group('f')
df_female

# Obtenemos los datos como un numpy-array
values_female = df_female.values
values_female

import pandas as pd

df = pd.DataFrame([{'Name': 'Chris', 'Item Purchased': 'Sponge', 'Cost': 22.50},
                   {'Name': 'Kevyn', 'Item Purchased': 'Kitty Litter', 'Cost': 2.50},
                   {'Name': 'Filip', 'Item Purchased': 'Spoon', 'Cost': 5.00}],
                  index=['Store 1', 'Store 1', 'Store 2'])
df

df['Date'] = ['December 1', 'January 1', 'mid-May']
df

df['Delivered'] = True
df

df['Feedback'] = ['Positive', None, 'Negative']
df

adf = df.reset_index()
adf['Date'] = pd.Series({0: 'December 1', 2: 'mid-May'})
adf

staff_df = pd.DataFrame([{'Name': 'Kelly', 'Role': 'Director of HR'},
                         {'Name': 'Sally', 'Role': 'Course liasion'},
                         {'Name': 'James', 'Role': 'Grader'}])
staff_df = staff_df.set_index('Name')
student_df = pd.DataFrame([{'Name': 'James', 'School': 'Business'},
                           {'Name': 'Mike', 'School': 'Law'},
                           {'Name': 'Sally', 'School': 'Engineering'}])
student_df = student_df.set_index('Name')
print(staff_df.head())
print()
print(student_df.head())

pd.merge(staff_df, student_df, how='outer', left_index=True, right_index=True)

pd.merge(staff_df, student_df, how='inner', left_index=True, right_index=True)

pd.merge(staff_df, student_df, how='left', left_index=True, right_index=True)

pd.merge(staff_df, student_df, how='right', left_index=True, right_index=True)

staff_df = staff_df.reset_index()
student_df = student_df.reset_index()
pd.merge(staff_df, student_df, how='left', left_on='Name', right_on='Name')

staff_df = pd.DataFrame([{'Name': 'Kelly', 'Role': 'Director of HR', 'Location': 'State Street'},
                         {'Name': 'Sally', 'Role': 'Course liasion', 'Location': 'Washington Avenue'},
                         {'Name': 'James', 'Role': 'Grader', 'Location': 'Washington Avenue'}])
student_df = pd.DataFrame([{'Name': 'James', 'School': 'Business', 'Location': '1024 Billiard Avenue'},
                           {'Name': 'Mike', 'School': 'Law', 'Location': 'Fraternity House #22'},
                           {'Name': 'Sally', 'School': 'Engineering', 'Location': '512 Wilson Crescent'}])
pd.merge(staff_df, student_df, how='left', left_on='Name', right_on='Name')

staff_df = pd.DataFrame([{'First Name': 'Kelly', 'Last Name': 'Desjardins', 'Role': 'Director of HR'},
                         {'First Name': 'Sally', 'Last Name': 'Brooks', 'Role': 'Course liasion'},
                         {'First Name': 'James', 'Last Name': 'Wilde', 'Role': 'Grader'}])
student_df = pd.DataFrame([{'First Name': 'James', 'Last Name': 'Hammond', 'School': 'Business'},
                           {'First Name': 'Mike', 'Last Name': 'Smith', 'School': 'Law'},
                           {'First Name': 'Sally', 'Last Name': 'Brooks', 'School': 'Engineering'}])
staff_df
student_df
pd.merge(staff_df, student_df, how='inner', left_on=['First Name','Last Name'], right_on=['First Name','Last Name'])

df = pd.DataFrame(['A+', 'A', 'A-', 'B+', 'B', 'B-', 'C+', 'C', 'C-', 'D+', 'D'],
                  index=['excellent', 'excellent', 'excellent', 'good', 'good', 'good', 'ok', 'ok', 'ok', 'poor', 'poor'])
df.rename(columns={0: 'Grades'}, inplace=True)
df

df['Grades'].astype('category').head()

grades = pd.Categorical(df.Grades, categories=['D', 'D+', 'C-', 'C', 'C+', 'B-', 'B', 'B+', 'A-', 'A', 'A+'],
                              ordered=True)
grades

grades > 'C'

#import os as os
#os.chdir("C:/Users/VICTOR/Documents/AnalyticsPython/Data")
df = pd.read_csv('https://raw.githubusercontent.com/vmoprojs/DataLectures/master/census.csv')
df = df[df['SUMLEV']==50]
df = df.set_index('STNAME').groupby(level=0)['CENSUS2010POP'].agg([np.average]).rename(columns={'average': 'avg'})
pd.cut(df['avg'],10)

uu = "https://raw.githubusercontent.com/vmoprojs/DataLectures/master/cars.csv"
df = pd.read_csv(uu)
df.describe()

df.head()

df.pivot_table(values='(kW)', index='YEAR', columns='Make', aggfunc=np.mean)

df.pivot_table(values='(kW)', index='YEAR', columns='Make', aggfunc=[np.mean,np.min], margins=True)