access_dataframe_elements.py

import pandas as pd

# run the script with python 2.7 to get appropriate results
# Subway ridership for 5 stations on 10 different days
ridership_df = pd.DataFrame(
    data=[[   0,    0,    2,    5,    0],
          [1478, 3877, 3674, 2328, 2539],
          [1613, 4088, 3991, 6461, 2691],
          [1560, 3392, 3826, 4787, 2613],
          [1608, 4802, 3932, 4477, 2705],
          [1576, 3933, 3909, 4979, 2685],
          [  95,  229,  255,  496,  201],
          [   2,    0,    1,   27,    0],
          [1438, 3785, 3589, 4174, 2215],
          [1342, 4043, 4009, 4665, 3033]],
    index=['05-01-11', '05-02-11', '05-03-11', '05-04-11', '05-05-11',
           '05-06-11', '05-07-11', '05-08-11', '05-09-11', '05-10-11'],
    columns=['R003', 'R004', 'R005', 'R006', 'R007']
)

print ridership_df

# DataFrame creation
# You can create a DataFrame out of a dictionary mapping column names to values
df_1 = pd.DataFrame({'A': [0, 1, 2], 'B': [3, 4, 5]})
print df_1

# You can also use a list of lists or a 2D NumPy array
df_2 = pd.DataFrame([[0, 1, 2], [3, 4, 5]], columns=['A', 'B', 'C'])
print df_2


# Accessing elements
print ridership_df.iloc[0]
print ridership_df.loc['05-05-11']
print ridership_df['R003']
print ridership_df.iloc[1, 3]

# Accessing multiple rows
print ridership_df.iloc[1:4]

# Accessing multiple columns
print ridership_df[['R003', 'R005']]

# Pandas axis
df = pd.DataFrame({'A': [0, 1, 2], 'B': [3, 4, 5]})
print df.sum()
print df.sum(axis=1)
print df.values.sum()


def mean_riders_for_max_station(ridership):
    '''
    Fill in this function to find the station with the maximum riders on the
    first day, then return the mean riders per day for that station. Also
    return the mean ridership overall for comparsion.

    This is the same as a previous exercise, but this time the
    input is a Pandas DataFrame rather than a 2D NumPy array.
    '''
    pos_for_max_station_first_day = ridership.iloc[0].idxmax()
    overall_mean = ridership.values.mean()
    mean_for_max = ridership[pos_for_max_station_first_day].mean()

    return (overall_mean, mean_for_max)


print mean_riders_for_max_station(ridership_df)