Introduction to Importing Data in Python

# Open a file: file
file = open('moby_dick.txt', mode = 'r')

# Print it
print(file.read())

# Check whether file is closed
print(file.closed)

# Close file
file.close()

# Check whether file is closed
print(file.closed)

# Read & print the first 3 lines
with open('moby_dick.txt') as file:
    print(file.readline())
    print(file.readline())
    print(file.readline())

# Import pandas as pd
import pandas as pd

# Assign the filename: file
file = 'titanic.csv'

# Read the file into a DataFrame: df
df = pd.read_csv(file)

# View the head of the DataFrame
print(df.head())

# Assign the filename: file
file = 'digits.csv'

# Read the first 5 rows of the file into a DataFrame: data
data = pd.read_csv(file, nrows=5, header=None)

# Build a numpy array from the DataFrame: data_array
data_array = data.values

# Print the datatype of data_array to the shell
print(type(data_array))

# Import matplotlib.pyplot as plt
import matplotlib.pyplot as plt

# Assign filename: file
file = 'titanic_corrupt.txt'

# Import file: data, all text following '#' are considered comments, 'Nothing' is considered NA's
data = pd.read_csv(file, sep='\t', comment='#', na_values='Nothing')

# Print the head of the DataFrame
print(data.head())

# Plot 'Age' variable in a histogram
pd.DataFrame.hist(data[['Age']])
plt.xlabel('Age (years)')
plt.ylabel('count')
plt.show()

# Import pandas
import pandas as pd

# Assign spreadsheet filename: file
file = 'battledeath.xlsx'

# Load spreadsheet: xls
xls = pd.ExcelFile(file)

# Print sheet names
print(xls.sheet_names)

# Load a sheet into a DataFrame by name: df1
df1 = xls.parse('2004')

# Print the head of the DataFrame df1
print(df1.head())

# Load a sheet into a DataFrame by index: df2
df2 = xls.parse(0)

# Print the head of the DataFrame df2
print(df2.head())

# Parse the first sheet and rename the columns: df1
df1 = xls.parse(0, skiprows=[0], names=list(['Country','AAM due to War (2002)']))

# Print the head of the DataFrame df1
print(df1.head())

# Parse the first column of the second sheet and rename the column: df2
df2 = xls.parse(1, usecols=[0], skiprows=[0], names=['Country'])

# Print the head of the DataFrame df2
print(df2.head())