diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index 91557cd..bed5d60 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..1a766c6 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..446fe00 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..0bc433b 100644 --- a/q01_load_data/build.py +++ b/q01_load_data/build.py @@ -1,10 +1,20 @@ +# %load q01_load_data/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split - +path = './data/olympics.csv' def q01_load_data(path): - "write your solution here" + df = pd.read_csv(path,header=0, skiprows=1) # use .read_csv function to read the # data and header=0 to skip the first row + c = list(df.columns) + c [0] = 'country name' + df.columns = c + return df + +df = q01_load_data(path) +type(df) +df.shape + diff --git a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc index 46496ca..7448c6a 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..73d9a76 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..d644a29 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..e42bb09 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..5b746d3 100644 --- a/q02_rename_columns/build.py +++ b/q02_rename_columns/build.py @@ -1,9 +1,17 @@ +# %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 - +path = './data/olympics.csv' 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.rename(columns={'01 !':'Gold', '02 !':'Silver', '03 !':'Bronze'}, inplace=True) + return df + +q02_rename_columns(path) + + + + diff --git a/q02_rename_columns/tests/__pycache__/__init__.cpython-36.pyc b/q02_rename_columns/tests/__pycache__/__init__.cpython-36.pyc index 198a898..ac494d3 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..d9e01af 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..4034a5b 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..3228651 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..f27ecce 100644 --- a/q03_split_country/build.py +++ b/q03_split_country/build.py @@ -1,10 +1,21 @@ +# %load q03_split_country/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from greyatomlib.olympics_project.q02_rename_columns.build import q02_rename_columns - +path = './data/olympics.csv' 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 + country_names = df['country name'] + s = country_names.apply(lambda x : x.split()[0]) + df['country'] = s + df.set_index('country', inplace=True) +# df.drop(['Total'], axis=1, inplace=True) + df.drop(['country name'], axis=1, inplace=True) + return df[:-1] +df = q03_summer_gold_medals(path) +df.shape + + diff --git a/q03_split_country/tests/__pycache__/__init__.cpython-36.pyc b/q03_split_country/tests/__pycache__/__init__.cpython-36.pyc index 6015fed..82aab2c 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..b23df87 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 diff --git a/q04_country_with_most_gold_medals/__pycache__/__init__.cpython-36.pyc b/q04_country_with_most_gold_medals/__pycache__/__init__.cpython-36.pyc index 5be5c53..43010b2 100644 Binary files a/q04_country_with_most_gold_medals/__pycache__/__init__.cpython-36.pyc and b/q04_country_with_most_gold_medals/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_country_with_most_gold_medals/__pycache__/build.cpython-36.pyc b/q04_country_with_most_gold_medals/__pycache__/build.cpython-36.pyc index edf8f75..b8fe028 100644 Binary files a/q04_country_with_most_gold_medals/__pycache__/build.cpython-36.pyc and b/q04_country_with_most_gold_medals/__pycache__/build.cpython-36.pyc differ diff --git a/q04_country_with_most_gold_medals/build.py b/q04_country_with_most_gold_medals/build.py index 27251ef..dfeb555 100644 --- a/q04_country_with_most_gold_medals/build.py +++ b/q04_country_with_most_gold_medals/build.py @@ -1,11 +1,21 @@ +# %load q04_country_with_most_gold_medals/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from greyatomlib.olympics_project.q03_split_country.build import q03_summer_gold_medals - +path = './data/olympics.csv' def q04_country_with_most_gold_medals(path): - "write your solution here" + df = q03_summer_gold_medals(path) - + d = df.Gold + v = d.iloc[:,2].astype(int) + country_with_most_golds = v.nlargest(1).index[0].strip() + return country_with_most_golds + + +q04_country_with_most_gold_medals(path) + + + diff --git a/q04_country_with_most_gold_medals/tests/__pycache__/__init__.cpython-36.pyc b/q04_country_with_most_gold_medals/tests/__pycache__/__init__.cpython-36.pyc index e7d7d49..6927c7a 100644 Binary files a/q04_country_with_most_gold_medals/tests/__pycache__/__init__.cpython-36.pyc and b/q04_country_with_most_gold_medals/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_country_with_most_gold_medals/tests/__pycache__/test.cpython-36.pyc b/q04_country_with_most_gold_medals/tests/__pycache__/test.cpython-36.pyc index b79dc60..f0b84a6 100644 Binary files a/q04_country_with_most_gold_medals/tests/__pycache__/test.cpython-36.pyc and b/q04_country_with_most_gold_medals/tests/__pycache__/test.cpython-36.pyc differ diff --git a/q05_difference_in_gold_medal/__pycache__/__init__.cpython-36.pyc b/q05_difference_in_gold_medal/__pycache__/__init__.cpython-36.pyc index 2001848..8c9a3bb 100644 Binary files a/q05_difference_in_gold_medal/__pycache__/__init__.cpython-36.pyc and b/q05_difference_in_gold_medal/__pycache__/__init__.cpython-36.pyc differ diff --git a/q05_difference_in_gold_medal/__pycache__/build.cpython-36.pyc b/q05_difference_in_gold_medal/__pycache__/build.cpython-36.pyc index ff681a3..0047a20 100644 Binary files a/q05_difference_in_gold_medal/__pycache__/build.cpython-36.pyc and b/q05_difference_in_gold_medal/__pycache__/build.cpython-36.pyc differ diff --git a/q05_difference_in_gold_medal/build.py b/q05_difference_in_gold_medal/build.py index 9fb11ec..d058264 100644 --- a/q05_difference_in_gold_medal/build.py +++ b/q05_difference_in_gold_medal/build.py @@ -1,9 +1,16 @@ +# %load q05_difference_in_gold_medal/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from greyatomlib.olympics_project.q02_rename_columns.build import q02_rename_columns - -def q05_difference_in_gold_medal(): - "write your solution here" +path = './data/olympics.csv' +def q05_difference_in_gold_medal(path): + df = q02_rename_columns(path) + d = df.Gold + v = abs(d.iloc[:,0].astype(int) - d.iloc[:,1].astype(int)) + return v.nlargest(2).iloc[1,] + + + diff --git a/q05_difference_in_gold_medal/tests/__pycache__/__init__.cpython-36.pyc b/q05_difference_in_gold_medal/tests/__pycache__/__init__.cpython-36.pyc index 7b04315..0ede05f 100644 Binary files a/q05_difference_in_gold_medal/tests/__pycache__/__init__.cpython-36.pyc and b/q05_difference_in_gold_medal/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q05_difference_in_gold_medal/tests/__pycache__/test.cpython-36.pyc b/q05_difference_in_gold_medal/tests/__pycache__/test.cpython-36.pyc index efd000f..e14d84a 100644 Binary files a/q05_difference_in_gold_medal/tests/__pycache__/test.cpython-36.pyc and b/q05_difference_in_gold_medal/tests/__pycache__/test.cpython-36.pyc differ diff --git a/q06_get_points/__pycache__/__init__.cpython-36.pyc b/q06_get_points/__pycache__/__init__.cpython-36.pyc index 7c1cf4d..4a14f5c 100644 Binary files a/q06_get_points/__pycache__/__init__.cpython-36.pyc and b/q06_get_points/__pycache__/__init__.cpython-36.pyc differ diff --git a/q06_get_points/__pycache__/build.cpython-36.pyc b/q06_get_points/__pycache__/build.cpython-36.pyc index d45fe38..87c35f4 100644 Binary files a/q06_get_points/__pycache__/build.cpython-36.pyc and b/q06_get_points/__pycache__/build.cpython-36.pyc differ diff --git a/q06_get_points/build.py b/q06_get_points/build.py index 4f4afd7..734102f 100644 --- a/q06_get_points/build.py +++ b/q06_get_points/build.py @@ -1,9 +1,20 @@ +# %load q06_get_points/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from greyatomlib.olympics_project.q02_rename_columns.build import q02_rename_columns -path = "data/olympics.csv" +path = 'data/olympics.csv' + +def q06_get_points(path): + df = q02_rename_columns(path) + g = df.Gold.astype(int) * 3 + s = df.Silver.astype(int) * 2 + b = df.Bronze.astype(int) * 1 + total_points = g.iloc[:,0] + g.iloc[:,1] + s.iloc[:,0] + s.iloc[:,1] +b.iloc[:,0] + b.iloc[:,1] + df['Points'] = total_points + return df.Points + diff --git a/q06_get_points/tests/__pycache__/__init__.cpython-36.pyc b/q06_get_points/tests/__pycache__/__init__.cpython-36.pyc index 7db8f24..47dfbf5 100644 Binary files a/q06_get_points/tests/__pycache__/__init__.cpython-36.pyc and b/q06_get_points/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q06_get_points/tests/__pycache__/test.cpython-36.pyc b/q06_get_points/tests/__pycache__/test.cpython-36.pyc index 8cccf4a..ea96411 100644 Binary files a/q06_get_points/tests/__pycache__/test.cpython-36.pyc and b/q06_get_points/tests/__pycache__/test.cpython-36.pyc differ