# %load q02_get_unique_values/build.py
from greyatomlib.pandas_project.q01_read_csv_data_to_df.build import read_csv_data_to_df
# You have been given the dataset already in 'ipl_df'.
ipl_df = read_csv_data_to_df('data/ipl_dataset.csv')
ipl_df
#Solution
def get_unique_venues():
a = ipl_df['venue'].unique()
return a
get_unique_venues()
# Default Imports
from greyatomlib.pandas_project.q01_read_csv_data_to_df.build import read_csv_data_to_df
# You have been given dataset already in 'ipl_df'.
ipl_df = read_csv_data_to_df(
"/home/darshind/Workspace/code/pandas_project/data/ipl_dataset.csv")
# Solution
def get_match_innings_runs():
filtered_data = ipl_df[['match_code', 'inning', 'runs']]
return filtered_data.groupby(['match_code', 'inning']).sum()
print get_match_innings_runs()
# Default Imports
from greyatomlib.pandas_project.q01_read_csv_data_to_df.build import read_csv_data_to_df
# You have been given the dataset already in 'ipl_df'.
ipl_df = read_csv_data_to_df("./data/ipl_dataset.csv")
# Solution
def get_run_counts():
return ipl_df['runs'].value_counts()
def create_bowler_filter(bowler):
ipl_df = read_csv_data_to_df('./data/ipl_dataset.csv')
bowler_df = ipl_df.loc[ipl_df['bowler'] == bowler]
bowler_series = pd.Series(bowler_df['bowler'])
return bowler_series.count()
def get_unique_venues():
ipl_df = read_csv_data_to_df('data/ipl_dataset.csv')
return ipl_df['venue'].unique()
def get_run_counts():
ipl_df = read_csv_data_to_df('./data/ipl_dataset.csv')
runs_count = ipl_df['runs'].value_counts()
count_series = pd.Series(runs_count)
return count_series
def create_bowler_filter(bowler):
ipl_df = read_csv_data_to_df('./data/ipl_dataset.csv')
return(ipl_df['bowler']==bowler)
def get_run_counts():
ipl_df = read_csv_data_to_df('./data/ipl_dataset.csv')
runs_count= ipl_df['runs'].value_counts()
return runs_count
def test_get_unique_venues(self):
path = "./data/ipl_dataset.csv"
ipl_df = read_csv_data_to_df(path)
venues = get_unique_venues()
self.assertTrue(35 == len(venues))
import pandas as pd
from greyatomlib.pandas_project.q01_read_csv_data_to_df.build import read_csv_data_to_df
path = "./data/ipl_dataset.csv"
ipl_df = read_csv_data_to_df(path)
def get_run_counts():
runs_count = pd.Series.value_counts(ipl_df['runs'])
return runs_count
def get_match_specific_df(mt_code):
ipl_df = read_csv_data_to_df("./data/ipl_dataset.csv")
return ipl_df[ipl_df['match_code'] == mt_code]
# %load q07_get_run_counts_by_match/build.py
# Default Imports
from greyatomlib.pandas_project.q01_read_csv_data_to_df.build import read_csv_data_to_df
import pandas as pd
import numpy as np
# You have been give the dataset already in 'ipl_df'.
ipl_df = pd.DataFrame(read_csv_data_to_df('./data/ipl_dataset.csv'))
# Solution
def get_runs_counts_by_match():
a = pd.DataFrame(
ipl_df.pivot_table(index='match_code', columns='runs',
aggfunc='count'))
return (a['batsman'])
print(get_runs_counts_by_match())
def get_match_specific_df(match_code):
ipl_df = read_csv_data_to_df('./data/ipl_dataset.csv')
match_data = ipl_df.loc[ipl_df['match_code'] == match_code]
return match_data
def get_runs_counts_by_match():
ipl_df = read_csv_data_to_df("./data/ipl_dataset.csv")
return ipl_df.pivot_table(values='total',
index='match_code',
columns=['runs'],
aggfunc='count')
def get_match_innings_runs():
ipl_df = read_csv_data_to_df('data/ipl_dataset.csv')
df = ipl_df.groupby('match_code').sum()
return df[['runs']]
def get_match_innings_runs():
ipl_df = read_csv_data_to_df("data/ipl_dataset.csv")
return ipl_df.groupby(['match_code', 'inning'])['runs'].sum()
