diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index 91557cd..9224d25 100644 Binary files a/__pycache__/__init__.cpython-36.pyc and b/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_load_data/__pycache__/__init__.cpython-36.pyc b/q01_load_data/__pycache__/__init__.cpython-36.pyc index 5e9e2e2..a05783c 100644 Binary files a/q01_load_data/__pycache__/__init__.cpython-36.pyc and b/q01_load_data/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_load_data/__pycache__/build.cpython-36.pyc b/q01_load_data/__pycache__/build.cpython-36.pyc index 6ba929f..f5b5543 100644 Binary files a/q01_load_data/__pycache__/build.cpython-36.pyc and b/q01_load_data/__pycache__/build.cpython-36.pyc differ diff --git a/q01_load_data/build.py b/q01_load_data/build.py index 1a26cc1..728458f 100644 --- a/q01_load_data/build.py +++ b/q01_load_data/build.py @@ -1,10 +1,19 @@ +# %load q01_load_data/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split def q01_load_data(path): - "write your solution here" + 'write your solution here' # use .read_csv function to read the # data and header=0 to skip the first row + df = pd.read_csv(path, header=0) + new_header = df.iloc[0] # grab the first row for the header + new_header[0] = 'country name' + df = df[1:] # take the data less the header row + df.columns = new_header # set the header row as the df header + return df + + diff --git a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc index 46496ca..7ae5cf7 100644 Binary files a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc and b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_load_data/tests/__pycache__/test.cpython-36.pyc b/q01_load_data/tests/__pycache__/test.cpython-36.pyc index 0dc2257..8c0c114 100644 Binary files a/q01_load_data/tests/__pycache__/test.cpython-36.pyc and b/q01_load_data/tests/__pycache__/test.cpython-36.pyc differ diff --git a/q02_rename_columns/__pycache__/__init__.cpython-36.pyc b/q02_rename_columns/__pycache__/__init__.cpython-36.pyc index 687491c..b9a7413 100644 Binary files a/q02_rename_columns/__pycache__/__init__.cpython-36.pyc and b/q02_rename_columns/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_rename_columns/__pycache__/build.cpython-36.pyc b/q02_rename_columns/__pycache__/build.cpython-36.pyc index 28092f5..cbb8fcc 100644 Binary files a/q02_rename_columns/__pycache__/build.cpython-36.pyc and b/q02_rename_columns/__pycache__/build.cpython-36.pyc differ diff --git a/q02_rename_columns/build.py b/q02_rename_columns/build.py index 20dd8e9..dab10c7 100644 --- a/q02_rename_columns/build.py +++ b/q02_rename_columns/build.py @@ -1,9 +1,14 @@ +# %load q02_rename_columns/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from greyatomlib.olympics_project.q01_load_data.build import q01_load_data def q02_rename_columns(path): - "write your solution here" + 'write your solution here' df = q01_load_data(path) - \ No newline at end of file + df.columns = ['country name', '# Summer', 'Gold', 'Silver', 'Bronze', 'Total', '# Winter', 'Gold', 'Silver', 'Bronze','Total', '# Games', 'Gold', 'Silver', 'Bronze', 'Combined total'] + return df + + + diff --git a/q02_rename_columns/tests/__pycache__/__init__.cpython-36.pyc b/q02_rename_columns/tests/__pycache__/__init__.cpython-36.pyc index 198a898..16de172 100644 Binary files a/q02_rename_columns/tests/__pycache__/__init__.cpython-36.pyc and b/q02_rename_columns/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_rename_columns/tests/__pycache__/test.cpython-36.pyc b/q02_rename_columns/tests/__pycache__/test.cpython-36.pyc index 1c28f5b..1692c4a 100644 Binary files a/q02_rename_columns/tests/__pycache__/test.cpython-36.pyc and b/q02_rename_columns/tests/__pycache__/test.cpython-36.pyc differ diff --git a/q03_split_country/__pycache__/__init__.cpython-36.pyc b/q03_split_country/__pycache__/__init__.cpython-36.pyc index e71d6ad..1296dd7 100644 Binary files a/q03_split_country/__pycache__/__init__.cpython-36.pyc and b/q03_split_country/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_split_country/__pycache__/build.cpython-36.pyc b/q03_split_country/__pycache__/build.cpython-36.pyc index 5935601..b35626d 100644 Binary files a/q03_split_country/__pycache__/build.cpython-36.pyc and b/q03_split_country/__pycache__/build.cpython-36.pyc differ diff --git a/q03_split_country/build.py b/q03_split_country/build.py index 6c075fb..63bdc4b 100644 --- a/q03_split_country/build.py +++ b/q03_split_country/build.py @@ -1,3 +1,4 @@ +# %load q03_split_country/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split @@ -5,6 +6,22 @@ def q03_summer_gold_medals(path): - "write your solution here" + 'write your solution here' df = q02_rename_columns(path) - \ No newline at end of file + a = df['country name'] + b = a.str.split('(',expand=True) + c = b[0] +# d = b[1] +# e = d.str.split(')', expand=True) +# f = list(e[0]) + df = df.set_index(c) +# df['country code'] = f + df.drop(['Totals'], axis = 0, inplace = True) + df.drop(['country name'], axis = 1, inplace = True) + df.index.name = 'country name' + return df + +# path = 'data/olympics.csv' +# q03_summer_gold_medals(path) + + diff --git a/q03_split_country/tests/__pycache__/__init__.cpython-36.pyc b/q03_split_country/tests/__pycache__/__init__.cpython-36.pyc index 6015fed..2f24b31 100644 Binary files a/q03_split_country/tests/__pycache__/__init__.cpython-36.pyc and b/q03_split_country/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_split_country/tests/__pycache__/test.cpython-36.pyc b/q03_split_country/tests/__pycache__/test.cpython-36.pyc index 51cbfae..6e86922 100644 Binary files a/q03_split_country/tests/__pycache__/test.cpython-36.pyc and b/q03_split_country/tests/__pycache__/test.cpython-36.pyc differ