Import

$ data = np.genfromtxt('titanic.csv', delimiter=',', names=True, dtype=None)

$ np.recfromcsv(‘file_name’, nrows= 5, header = None)

$ pd.read_csv()

$ pd.read_table()

data = pd.read_csv(file, sep='\t', comment='#', na_values='Nothing')

 

Magics: 

!ls 

import os

wd = os.getcwd()

os.listdir(wd)

df1 = xls.parse(0, skiprows= 1, names=['Country', 'AAM due to War (2002)'])

df2 = xls.parse(0, usecols= 0, skiprows=1, names=['z', 'A'])

 

# Get the HDF5 group: group

group = data['strain']

 

# Check out keys of group

for key in group.keys():

    print(key)

# Set variable equal to time series data: strain

strain = data['strain']['Strain'].value

# Set number of time points to sample: num_samples

num_samples = 10000

# Set time vector

time = np.arange(0, 1, 1/num_samples)

# Plot data

plt.plot(time, strain[:num_samples])

plt.xlabel('GPS Time (s)')

plt.ylabel('strain')

plt.show()

# Print the keys of the MATLAB dictionary

print(mat.keys())

# Print the type of the value corresponding to the key 'CYratioCyt'

print(type(mat['CYratioCyt']))

# Print the shape of the value corresponding to the key 'CYratioCyt'

print(mat['CYratioCyt'].shape)

# Subset the array and plot it

data = mat['CYratioCyt'][25, 5:]

fig = plt.figure()

plt.plot(data)

plt.xlabel('time (min.)')

plt.ylabel('normalized fluorescence (measure of expression)')

plt.show()

# Import necessary module

from sqlalchemy import create_engine

# Create engine: engine

engine = create_engine('sqlite:///Chinook.SQLite')

# Import necessary module

from sqlalchemy import create_engine

# Create engine: engine

engine = create_engine('sqlite:///Chinook.sqlite')

# Save the table names to a list: table_names

table_names = engine.table_names()

# Print the table names to the shell

print(table_names)

# Import packages

from sqlalchemy import create_engine

import pandas as pd

# Create engine: engine

engine = create_engine('sqlite:///Chinook.sqlite')

# Open engine connection: con

con = engine.connect()

# Perform query: rs

rs = con.execute("SELECT * FROM album")

# Save results of the query to DataFrame: df

df = pd.DataFrame(rs.fetchall())

# Close connection

con.close()

# Print head of DataFrame df

print(df.head())

# Open engine in context manager

# Perform query and save results to DataFrame: df

with engine.connect() as con:

    rs = con.execute("SELECT LastName, Title FROM Employee")

    df = pd.DataFrame(rs.fetchmany(size=3))

    df.columns = rs.keys()

# Open engine in context manager

# Perform query and save results to DataFrame: df

with engine.connect() as con:

    rs = con.execute("SELECT * FROM Employee WHERE EmployeeId >= 6")

    df = pd.DataFrame(rs.fetchall())

    df.columns = rs.keys()

with engine.connect() as con:

    rs = con.execute("SELECT * FROM Employee ORDER BY BirthDate")

    df = pd.DataFrame(rs.fetchall())

# Execute query and store records in DataFrame: df

df = pd.read_sql_query("SELECT * FROM album", engine)

df = pd.read_sql_query("SELECT * FROM Employee WHERE EmployeeId >= 6 ORDER BY BirthDate", engine)

with engine.connect() as con:

    rs=con.execute("SELECT Title, Name FROM Album INNER JOIN Artist on Album.ArtistID = Artist.ArtistID")

    df=pd.DataFrame(rs.fetchall())

    df.columns=rs.keys()

df = pd.read_sql_query("SELECT * FROM PlaylistTrack INNER JOIN Track on PlaylistTrack.TrackId = Track.TrackId WHERE Milliseconds < 250000", engine)