whow i fill the data if most values are nan in jupyter notebook code example

Example 1: whow i fill the data if most values are nan in jupyter notebook

# import pandas
import pandas as pd

# make a sample data
list_of_rows = [
  {'start_station': 1, 'end_station': 1},
  {'start_station': None, 'end_station': 1},
  {'start_station': 1, 'end_station': 2},
  {'start_station': 1, 'end_station': 3},
  {'start_station': 2, 'end_station': None},
  {'start_station': 2, 'end_station': 3},
  {'start_station': 2, 'end_station': 3},
]

# make a pandas data frame
df = pd.DataFrame(list_of_rows)

# define a function
def fill_NaNs_in_end_station(row):
    if pd.isnull(row['end_station']):
        start_station = row['start_station']
        return df[df['start_station']==start_station].end_station.value_counts().first_valid_index()
    return row['end_station']

# apply function to dataframe
df['end_station'] = df.apply(lambda row: fill_NaNs_in_end_station(row), axis=1)

Example 2: handling missing dvalues denoted by a '?' in pandas

# Making a list of missing value typesmissing_values = ["n/a", "na", "--"]df = pd.read_csv("property data.csv", na_values = missing_values)