summarizingdata.py

# -*- coding: utf-8 -*-
"""SummarizingData.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1Wo7aUHTjFTRVpiK4efjRHI2gsA6fRip5
"""

# Import pandas
import pandas as pd

# Use pandas to read in recent_grads_url
recent_grads = pd.read_csv("/content/recent_grads.csv")

# Print the shape
print(recent_grads.shape)

from google.colab import drive
drive.mount('/content/drive')

# Print .dtypes
print(recent_grads.dtypes)

# Output summary statistics
print(recent_grads.describe())

# Exclude data of type object
print(recent_grads.describe(exclude=["object"]))

# Names of the columns we're searching for missing values
columns = ['median', 'p25th', 'p75th']

# Take a look at the dtypes
print(recent_grads[columns].dtypes)

# Find how missing values are represented
print(recent_grads["median"].unique())

# Replace missing values with NaN
for column in columns:
    recent_grads.loc[recent_grads[column] == 'UN', column] = np.nan

import numpy as np
import pandas as pd

# Assuming 'recent_grads' is your DataFrame and 'columns' is a list of columns needing correction

# Replace missing values with NaN
for column in columns:
    recent_grads.loc[recent_grads[column] == 'UN', column] = np.nan

# Select sharewomen column
sw_col = recent_grads['sharewomen']

# Output first five rows
print(sw_col.head())

# Import numpy
import numpy as np

# Use max to output maximum values
max_sw = recent_grads['sharewomen'].max()

# Print column max
print(max_sw)

# Output the row containing the maximum percentage of women
#print(sw_col)
print(recent_grads[(recent_grads['sharewomen']==max_sw)])

# Convert to numpy array
import numpy as np
recent_grads_np=np.array(recent_grads[['unemployed', 'low_wage_jobs']])


# Print the type of recent_grads_np
print(type(recent_grads_np))

print(np.corrcoef(recent_grads_np[:,0], recent_grads_np[:,1]))