Python(Exploratory Data Queries)1

Basics OF EXPLORATORY Python Analysis

==============================================
##Loadiing And Importing Pickled File
##Exercise B1.1
==============================================

# Importing pickled package
import pickle

# Opening pickle file and loading data: d
with open('data.pkl', 'rb') as file:
    d = pickle.load(file)

# Print d
print(d)

# Print datatype of d
print(type(d))

++++++++++++++++++++++++++++++++++++++++++++++++++++

==============================================
##Loading And Importing Spreadsheet
##Exercise B2.1
==============================================

# Import pandas
import pandas as pd

# Assigning spreadsheet filename: file
file = 'filepath.xlsx'

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

# Printing sheet names
print(xls.sheet_names)

==============================================
##Loading Individual Sheetname From A Spreadsheet
##Exercise B3.1
==============================================

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

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

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

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

==============================================
##Parse:  Loading In Between Spreadsheet
##Exercise B4.1
==============================================

# Parsing the first sheet and renaming the columns: df1

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

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

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

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

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

==============================================
##Loading And Importing: SAS AND STATA File
##Exercise B5.1
==============================================

##Importing Needed Library
import pandas as pd
import matplotlib.pyplot as plt

# Import sas7bdat package
from sas7bdat import SAS7BDAT

# Saving file to a DataFrame: df_sas
with SAS7BDAT('filepath.sas7bdat') as file:
   df_sas = file.to_data_frame()

# Printing head of DataFrame
print(df_sas.head())

# Ploting histogram of DataFrame features (pandas and pyplot already imported)
pd.DataFrame.hist(df_sas[['P']])
plt.ylabel('count')
plt.show()


==============================================
##Loading And Importing: SAS AND STATA File  in DF
##Exercise B6.1
==============================================
import pandas as pd
df = pd.read_stata('filepath.dta')


# Load Stata file into a pandas DataFrame: df
df = pd.read_stata('disarea.dta')

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

# Plot histogram of one column of the DataFrame
pd.DataFrame.hist(df[['disa10']])
plt.xlabel('Extent of disease')
plt.ylabel('Number of countries')
plt.show()

+++++++++++++++++++++++++++++++++++++++++++++++++++++

==============================================
##Loading And Importing: HDF5 File
##Exercise B7.1
==============================================
##Importing Libraries
import pandas as pd
import h5py
import matplotlib.pyplot as plt

# Assigning filename: file
file = 'filepath.hdf5' 

# Loading file: data
data = h5py.File(file, 'r')

# Printing the datatype of the loaded file
print(type(data))

# Printing the keys of the file
for key in data.keys():
    print(key)

==============================================
##Loading And Importing: HDF5 File
##Exercise B8.1
==============================================

# Get the HDF5 group: group
group = data['strain']

# Checking out keys of group
for key in group.keys():
    print(key)

# Setting variable equal to time series data: strain
strain = np.array(data['strain']['Strain'])

# Setting number of time points to sample: num_samples
num_samples = 10000

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

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

+++++++++++++++++++++++++++++++++++++++++++++++++++++

==============================================
##Loading And Importing: MATLAB File
##Exercise B9.1
==============================================

# Importing package
import scipy.io
import matplotlib.pyplot as plt
import numpy as np
______________________________________________

# Loading MATLAB file: mat
mat = scipy.io.loadmat('albeck_gene_expression.mat')

# Printing the datatype type of mat
print(type(mat))
plt.xlabel('GPS Time (s)')
plt.ylabel('strain')
plt.show()


==============================================
##Loading And Importing: MATLAB File
##Exercise B9.1
==============================================

# Printing the keys of the MATLAB dictionary
print(mat.keys())

# Printing the type of the value corresponding to the key 'CYratioCyt'
print(type(mat['CYratioCyt'][:9]))

# Printing the shape of the value corresponding to the key 'CYratioCyt'
print(np.shape(mat['CYratioCyt']))

# 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()