lakshay-arora

data.groupby(['name', pd.Grouper(key='date', freq='M')])['ext price'].sum()

lakshay-arora

data.groupby(['name', pd.Grouper(key='date', freq='M')])['ext price'].sum().unstack()

lakshay-arora

%matplotlib notebook
import matplotlib.pyplot as plt

# scatter plot of some data # try this on your dataset
plt.scatter(data['quantity'],data['unit price'])

lakshay-arora

%%time 
def myfunction(x) : 
    for i in range(1,100000,1) : 
        i=i+1

lakshay-arora

%load_ext rpy2.ipython
%R require(ggplot2)

lakshay-arora

import pandas as pd
df = pd.DataFrame({
        'Class': ['A', 'A', 'A', 'V', 'V', 'A', 'A', 'A'],
        'X': [4, 3, 5, 2, 1, 7, 7, 5],
        'Y': [0, 4, 3, 6, 7, 10, 11, 9],
        'Z': [1, 2, 3, 1, 2, 3, 1, 2]
    })

lakshay-arora

%%R -i df
ggplot(data = df) + geom_point(aes(x = X, y= Y, color = Class, size = Z))

lakshay-arora

# importing libraries
import pandas as pd
data = pd.read_csv('school.csv')

data.head()

lakshay-arora

# save the top cities in a list
top_cities = ['Brooklyn','Bronx','Manhattan','Jamaica','Long Island City']

# use loc to update the target
data.loc[(data.City.isin(top_cities) == False),'City'] = 'Others'

# city value counts
data.City.value_counts()

lakshay-arora

# importing required libraries
import pandas as pd
import math
import multiprocessing as mp
from random import randint

# function to calculate the number of divisors
def countDivisors(n) : 
    count = 0
    for i in range(1, (int)(math.sqrt(n)) + 1) :