From 09d032da1e57b3ce2aa7b9097085f4cf3c2990f3 Mon Sep 17 00:00:00 2001 From: ASPP Student Date: Wed, 24 Sep 2025 10:46:27 +0300 Subject: [PATCH 1/3] implemented tarot matching --- exercises/match_tarots/match_tarots.ipynb | 48 ++++++++++++++++++----- 1 file changed, 38 insertions(+), 10 deletions(-) diff --git a/exercises/match_tarots/match_tarots.ipynb b/exercises/match_tarots/match_tarots.ipynb index c35f220..9712ab3 100644 --- a/exercises/match_tarots/match_tarots.ipynb +++ b/exercises/match_tarots/match_tarots.ipynb @@ -27,7 +27,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 1, "id": "cf05b9c4", "metadata": {}, "outputs": [ @@ -36,9 +36,9 @@ "output_type": "stream", "text": [ "-- Deck 1: --\n", - " ['The Lovers', 'Temperance', 'The Emperor', 'The Sun', 'The Fool', 'The Chariot', 'Death', 'Strength', 'Justice', 'The Star', 'Judgement', 'The World', 'The Tower', 'The Hanged Man', 'The Empress', 'The Hermit', 'The Devil', 'The High Priestess', 'The Moon', 'The Hierophant', 'Wheel of Fortune', 'The Magician']\n", + " ['The Star', 'Justice', 'The Hanged Man', 'The Magician', 'The Hierophant', 'The High Priestess', 'The Chariot', 'The Emperor', 'The Fool', 'The Tower', 'The Devil', 'Strength', 'Judgement', 'The Moon', 'The Empress', 'The World', 'Wheel of Fortune', 'Death', 'The Lovers', 'The Sun', 'Temperance', 'The Hermit']\n", "-- Deck 2: --\n", - " ['The Fool', 'Death', 'The Hermit', 'Strength', 'The Moon', 'Wheel of Fortune', 'Judgement', 'The Lovers', 'The Star', 'The Hanged Man', 'The Empress', 'The Emperor', 'The Magician', 'The Tower', 'The Hierophant', 'The Chariot', 'The High Priestess', 'Temperance', 'The World', 'The Devil', 'The Sun', 'Justice']\n" + " ['The Lovers', 'The Chariot', 'Strength', 'The High Priestess', 'The Hermit', 'Justice', 'The Fool', 'Death', 'The Emperor', 'The Devil', 'The Star', 'The Sun', 'Judgement', 'The Hanged Man', 'The Hierophant', 'Wheel of Fortune', 'The Moon', 'The Magician', 'The Empress', 'Temperance', 'The Tower', 'The World']\n" ] } ], @@ -69,19 +69,47 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "id": "48eb31e2", "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "ename": "_IncompleteInputError", + "evalue": "incomplete input (4127308383.py, line 1)", + "output_type": "error", + "traceback": [ + "\u001b[0;36m Cell \u001b[0;32mIn[2], line 1\u001b[0;36m\u001b[0m\n\u001b[0;31m dict(keys = deck1, values = range(len(deck1))\u001b[0m\n\u001b[0m ^\u001b[0m\n\u001b[0;31m_IncompleteInputError\u001b[0m\u001b[0;31m:\u001b[0m incomplete input\n" + ] + } + ], + "source": [ + "dict(keys = deck1, values = range(len(de" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "id": "509dda71", "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{(15, 21), (11, 2), (8, 6), (10, 9), (9, 20), (12, 12), (20, 19), (4, 14), (5, 3), (14, 18), (19, 11), (0, 10), (1, 5), (6, 1), (18, 0), (13, 16), (2, 13), (16, 15), (17, 7), (3, 17), (21, 4), (7, 8)}\n" + ] + } + ], + "source": [ + " deck1_dict = {key:value for key,value in zip(deck1, list(range(len(deck1))))}\n", + " deck2_dict = {key:value for key,value in zip(deck2, list(range(len(deck1))))}\n", + "result = set()\n", + "for card in tarot_cards:\n", + " result.add((deck1_dict[card], deck2_dict[card]))\n", + "\n", + "print(result)\n", + " " + ] } ], "metadata": { @@ -100,7 +128,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.5" + "version": "3.13.6" } }, "nbformat": 4, -- 2.39.5 From a0ad8a4ba99dd9af73a28fe407b59044a9189f8f Mon Sep 17 00:00:00 2001 From: ASPP Student Date: Wed, 24 Sep 2025 10:49:31 +0300 Subject: [PATCH 2/3] implemented tarot matching --- exercises/match_tarots/match_tarots.ipynb | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/exercises/match_tarots/match_tarots.ipynb b/exercises/match_tarots/match_tarots.ipynb index 9712ab3..e62c9bd 100644 --- a/exercises/match_tarots/match_tarots.ipynb +++ b/exercises/match_tarots/match_tarots.ipynb @@ -67,25 +67,6 @@ "print(\"-- Deck 2: --\\n\", deck2)" ] }, - { - "cell_type": "code", - "execution_count": 2, - "id": "48eb31e2", - "metadata": {}, - "outputs": [ - { - "ename": "_IncompleteInputError", - "evalue": "incomplete input (4127308383.py, line 1)", - "output_type": "error", - "traceback": [ - "\u001b[0;36m Cell \u001b[0;32mIn[2], line 1\u001b[0;36m\u001b[0m\n\u001b[0;31m dict(keys = deck1, values = range(len(deck1))\u001b[0m\n\u001b[0m ^\u001b[0m\n\u001b[0;31m_IncompleteInputError\u001b[0m\u001b[0;31m:\u001b[0m incomplete input\n" - ] - } - ], - "source": [ - "dict(keys = deck1, values = range(len(de" - ] - }, { "cell_type": "code", "execution_count": 11, -- 2.39.5 From c49e81070e9e6a46ab7ee6bed513cabfa5c18799 Mon Sep 17 00:00:00 2001 From: ASPP Student Date: Wed, 24 Sep 2025 13:09:53 +0300 Subject: [PATCH 3/3] merged dataframes --- exercises/tabular_join/tabular_join.ipynb | 1290 ++++++++++++++++++++- 1 file changed, 1260 insertions(+), 30 deletions(-) diff --git a/exercises/tabular_join/tabular_join.ipynb b/exercises/tabular_join/tabular_join.ipynb index 6cf3ed9..be0b49a 100644 --- a/exercises/tabular_join/tabular_join.ipynb +++ b/exercises/tabular_join/tabular_join.ipynb @@ -10,7 +10,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "id": "b6f2742b", "metadata": {}, "outputs": [], @@ -30,7 +30,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 3, "id": "ed626ee3", "metadata": {}, "outputs": [ @@ -189,7 +189,7 @@ "4 No Yes No No 9 4.761123 No " ] }, - "execution_count": 2, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -201,7 +201,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 4, "id": "48d5375f", "metadata": {}, "outputs": [ @@ -275,7 +275,7 @@ "4 2 632 Control" ] }, - "execution_count": 3, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -326,12 +326,27 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 7, "id": "861ac334-14ce-490a-b3c4-877b32789f3e", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(6324, 16)\n" + ] + } + ], "source": [ - "## your code here\n" + "## your code here\n", + "\n", + "print(df.shape)\n", + "\n", + "identifier = ['location-id', 'patient-id']\n", + "\n", + "\n", + "\n" ] }, { @@ -344,12 +359,25 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 8, "id": "14f57842-5722-4953-88d6-d7cf3070400c", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(6287, 3)" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "## your code here\n" + "## your code here\n", + "\n", + "info.shape\n" ] }, { @@ -364,14 +392,553 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 10, + "id": "2dfaf171-2b81-4c7f-9101-c689aa56494d", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "\u001b[0;31mSignature:\u001b[0m\n", + "\u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmerge\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mleft\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'DataFrame | Series'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mright\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'DataFrame | Series'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mhow\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'MergeHow'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'inner'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mon\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'IndexLabel | AnyArrayLike | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mleft_on\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'IndexLabel | AnyArrayLike | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mright_on\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'IndexLabel | AnyArrayLike | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mleft_index\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mright_index\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0msort\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0msuffixes\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'Suffixes'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;34m'_x'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'_y'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'bool | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mindicator\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str | bool'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m \u001b[0mvalidate\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'str | None'\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n", + "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;34m'DataFrame'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mDocstring:\u001b[0m\n", + "Merge DataFrame or named Series objects with a database-style join.\n", + "\n", + "A named Series object is treated as a DataFrame with a single named column.\n", + "\n", + "The join is done on columns or indexes. If joining columns on\n", + "columns, the DataFrame indexes *will be ignored*. Otherwise if joining indexes\n", + "on indexes or indexes on a column or columns, the index will be passed on.\n", + "When performing a cross merge, no column specifications to merge on are\n", + "allowed.\n", + "\n", + ".. warning::\n", + "\n", + " If both key columns contain rows where the key is a null value, those\n", + " rows will be matched against each other. This is different from usual SQL\n", + " join behaviour and can lead to unexpected results.\n", + "\n", + "Parameters\n", + "----------\n", + "left : DataFrame or named Series\n", + "right : DataFrame or named Series\n", + " Object to merge with.\n", + "how : {'left', 'right', 'outer', 'inner', 'cross'}, default 'inner'\n", + " Type of merge to be performed.\n", + "\n", + " * left: use only keys from left frame, similar to a SQL left outer join;\n", + " preserve key order.\n", + " * right: use only keys from right frame, similar to a SQL right outer join;\n", + " preserve key order.\n", + " * outer: use union of keys from both frames, similar to a SQL full outer\n", + " join; sort keys lexicographically.\n", + " * inner: use intersection of keys from both frames, similar to a SQL inner\n", + " join; preserve the order of the left keys.\n", + " * cross: creates the cartesian product from both frames, preserves the order\n", + " of the left keys.\n", + "on : label or list\n", + " Column or index level names to join on. These must be found in both\n", + " DataFrames. If `on` is None and not merging on indexes then this defaults\n", + " to the intersection of the columns in both DataFrames.\n", + "left_on : label or list, or array-like\n", + " Column or index level names to join on in the left DataFrame. Can also\n", + " be an array or list of arrays of the length of the left DataFrame.\n", + " These arrays are treated as if they are columns.\n", + "right_on : label or list, or array-like\n", + " Column or index level names to join on in the right DataFrame. Can also\n", + " be an array or list of arrays of the length of the right DataFrame.\n", + " These arrays are treated as if they are columns.\n", + "left_index : bool, default False\n", + " Use the index from the left DataFrame as the join key(s). If it is a\n", + " MultiIndex, the number of keys in the other DataFrame (either the index\n", + " or a number of columns) must match the number of levels.\n", + "right_index : bool, default False\n", + " Use the index from the right DataFrame as the join key. Same caveats as\n", + " left_index.\n", + "sort : bool, default False\n", + " Sort the join keys lexicographically in the result DataFrame. If False,\n", + " the order of the join keys depends on the join type (how keyword).\n", + "suffixes : list-like, default is (\"_x\", \"_y\")\n", + " A length-2 sequence where each element is optionally a string\n", + " indicating the suffix to add to overlapping column names in\n", + " `left` and `right` respectively. Pass a value of `None` instead\n", + " of a string to indicate that the column name from `left` or\n", + " `right` should be left as-is, with no suffix. At least one of the\n", + " values must not be None.\n", + "copy : bool, default True\n", + " If False, avoid copy if possible.\n", + "\n", + " .. note::\n", + " The `copy` keyword will change behavior in pandas 3.0.\n", + " `Copy-on-Write\n", + " `__\n", + " will be enabled by default, which means that all methods with a\n", + " `copy` keyword will use a lazy copy mechanism to defer the copy and\n", + " ignore the `copy` keyword. The `copy` keyword will be removed in a\n", + " future version of pandas.\n", + "\n", + " You can already get the future behavior and improvements through\n", + " enabling copy on write ``pd.options.mode.copy_on_write = True``\n", + "indicator : bool or str, default False\n", + " If True, adds a column to the output DataFrame called \"_merge\" with\n", + " information on the source of each row. The column can be given a different\n", + " name by providing a string argument. The column will have a Categorical\n", + " type with the value of \"left_only\" for observations whose merge key only\n", + " appears in the left DataFrame, \"right_only\" for observations\n", + " whose merge key only appears in the right DataFrame, and \"both\"\n", + " if the observation's merge key is found in both DataFrames.\n", + "\n", + "validate : str, optional\n", + " If specified, checks if merge is of specified type.\n", + "\n", + " * \"one_to_one\" or \"1:1\": check if merge keys are unique in both\n", + " left and right datasets.\n", + " * \"one_to_many\" or \"1:m\": check if merge keys are unique in left\n", + " dataset.\n", + " * \"many_to_one\" or \"m:1\": check if merge keys are unique in right\n", + " dataset.\n", + " * \"many_to_many\" or \"m:m\": allowed, but does not result in checks.\n", + "\n", + "Returns\n", + "-------\n", + "DataFrame\n", + " A DataFrame of the two merged objects.\n", + "\n", + "See Also\n", + "--------\n", + "merge_ordered : Merge with optional filling/interpolation.\n", + "merge_asof : Merge on nearest keys.\n", + "DataFrame.join : Similar method using indices.\n", + "\n", + "Examples\n", + "--------\n", + ">>> df1 = pd.DataFrame({'lkey': ['foo', 'bar', 'baz', 'foo'],\n", + "... 'value': [1, 2, 3, 5]})\n", + ">>> df2 = pd.DataFrame({'rkey': ['foo', 'bar', 'baz', 'foo'],\n", + "... 'value': [5, 6, 7, 8]})\n", + ">>> df1\n", + " lkey value\n", + "0 foo 1\n", + "1 bar 2\n", + "2 baz 3\n", + "3 foo 5\n", + ">>> df2\n", + " rkey value\n", + "0 foo 5\n", + "1 bar 6\n", + "2 baz 7\n", + "3 foo 8\n", + "\n", + "Merge df1 and df2 on the lkey and rkey columns. The value columns have\n", + "the default suffixes, _x and _y, appended.\n", + "\n", + ">>> df1.merge(df2, left_on='lkey', right_on='rkey')\n", + " lkey value_x rkey value_y\n", + "0 foo 1 foo 5\n", + "1 foo 1 foo 8\n", + "2 bar 2 bar 6\n", + "3 baz 3 baz 7\n", + "4 foo 5 foo 5\n", + "5 foo 5 foo 8\n", + "\n", + "Merge DataFrames df1 and df2 with specified left and right suffixes\n", + "appended to any overlapping columns.\n", + "\n", + ">>> df1.merge(df2, left_on='lkey', right_on='rkey',\n", + "... suffixes=('_left', '_right'))\n", + " lkey value_left rkey value_right\n", + "0 foo 1 foo 5\n", + "1 foo 1 foo 8\n", + "2 bar 2 bar 6\n", + "3 baz 3 baz 7\n", + "4 foo 5 foo 5\n", + "5 foo 5 foo 8\n", + "\n", + "Merge DataFrames df1 and df2, but raise an exception if the DataFrames have\n", + "any overlapping columns.\n", + "\n", + ">>> df1.merge(df2, left_on='lkey', right_on='rkey', suffixes=(False, False))\n", + "Traceback (most recent call last):\n", + "...\n", + "ValueError: columns overlap but no suffix specified:\n", + " Index(['value'], dtype='object')\n", + "\n", + ">>> df1 = pd.DataFrame({'a': ['foo', 'bar'], 'b': [1, 2]})\n", + ">>> df2 = pd.DataFrame({'a': ['foo', 'baz'], 'c': [3, 4]})\n", + ">>> df1\n", + " a b\n", + "0 foo 1\n", + "1 bar 2\n", + ">>> df2\n", + " a c\n", + "0 foo 3\n", + "1 baz 4\n", + "\n", + ">>> df1.merge(df2, how='inner', on='a')\n", + " a b c\n", + "0 foo 1 3\n", + "\n", + ">>> df1.merge(df2, how='left', on='a')\n", + " a b c\n", + "0 foo 1 3.0\n", + "1 bar 2 NaN\n", + "\n", + ">>> df1 = pd.DataFrame({'left': ['foo', 'bar']})\n", + ">>> df2 = pd.DataFrame({'right': [7, 8]})\n", + ">>> df1\n", + " left\n", + "0 foo\n", + "1 bar\n", + ">>> df2\n", + " right\n", + "0 7\n", + "1 8\n", + "\n", + ">>> df1.merge(df2, how='cross')\n", + " left right\n", + "0 foo 7\n", + "1 foo 8\n", + "2 bar 7\n", + "3 bar 8\n", + "\u001b[0;31mFile:\u001b[0m /usr/lib64/python3.13/site-packages/pandas/core/reshape/merge.py\n", + "\u001b[0;31mType:\u001b[0m function" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "pd.merge?\n" + ] + }, + { + "cell_type": "code", + "execution_count": 12, "id": "35e19a53", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
patient-idlocation-idsexagesmokebmiwaistwthhtndiabhypercholfamhisthormop14toeventeventgroup
04364Male58Former33.531220.753086NoNoYesNoNo105.374401YesControl
111304Male77Current31.051190.730061YesYesNoNoNo106.097194NoControl
211314Female72Former30.861060.654321NoYesNoYesNo85.946612NoMedDiet + VOO
311324Male71Former27.681180.694118YesNoYesNoNo82.907598YesMedDiet + Nuts
411112Female79Never35.941290.806250YesNoYesNoNo94.761123NoMedDiet + VOO
......................................................
63191205Female66Never28.511040.645963YesNoYesYesNo83.550992NoControl
63201185Male80Never23.811090.589189YesYesYesYesNo82.743326NoControl
63213513Male57Former25.241000.571429YesNoYesNoNaN70.479124NoMedDiet + Nuts
63224995Female71Never32.04980.653333YesNoYesYesNo62.587269NoMedDiet + VOO
632312575Male58Former24.43930.547059YesYesYesNoNo92.590007NoMedDiet + Nuts
\n", + "

6324 rows × 17 columns

\n", + "
" + ], + "text/plain": [ + " patient-id location-id sex age smoke bmi waist wth \\\n", + "0 436 4 Male 58 Former 33.53 122 0.753086 \n", + "1 1130 4 Male 77 Current 31.05 119 0.730061 \n", + "2 1131 4 Female 72 Former 30.86 106 0.654321 \n", + "3 1132 4 Male 71 Former 27.68 118 0.694118 \n", + "4 1111 2 Female 79 Never 35.94 129 0.806250 \n", + "... ... ... ... ... ... ... ... ... \n", + "6319 120 5 Female 66 Never 28.51 104 0.645963 \n", + "6320 118 5 Male 80 Never 23.81 109 0.589189 \n", + "6321 351 3 Male 57 Former 25.24 100 0.571429 \n", + "6322 499 5 Female 71 Never 32.04 98 0.653333 \n", + "6323 1257 5 Male 58 Former 24.43 93 0.547059 \n", + "\n", + " htn diab hyperchol famhist hormo p14 toevent event group \n", + "0 No No Yes No No 10 5.374401 Yes Control \n", + "1 Yes Yes No No No 10 6.097194 No Control \n", + "2 No Yes No Yes No 8 5.946612 No MedDiet + VOO \n", + "3 Yes No Yes No No 8 2.907598 Yes MedDiet + Nuts \n", + "4 Yes No Yes No No 9 4.761123 No MedDiet + VOO \n", + "... ... ... ... ... ... ... ... ... ... \n", + "6319 Yes No Yes Yes No 8 3.550992 No Control \n", + "6320 Yes Yes Yes Yes No 8 2.743326 No Control \n", + "6321 Yes No Yes No NaN 7 0.479124 No MedDiet + Nuts \n", + "6322 Yes No Yes Yes No 6 2.587269 No MedDiet + VOO \n", + "6323 Yes Yes Yes No No 9 2.590007 No MedDiet + Nuts \n", + "\n", + "[6324 rows x 17 columns]" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "## your code here\n", "\n", - "\n" + "\n", + "df_merged = df.merge(info, how = \"left\", on = identifier)\n", + "df_merged" ] }, { @@ -388,7 +955,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 14, "id": "36ce0688-d421-4a07-b00e-0e9b3201f0e0", "metadata": {}, "outputs": [ @@ -456,7 +1023,7 @@ "4 5 Malaga" ] }, - "execution_count": 8, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -469,12 +1036,342 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 16, "id": "b636dde4-129a-4dd1-8cbf-c539c9c8a5f2", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
patient-idlocation-idsexagesmokebmiwaistwthhtndiabhypercholfamhisthormop14toeventeventgroupCity
04364Male58Former33.531220.753086NoNoYesNoNo105.374401YesControlBilbao
111304Male77Current31.051190.730061YesYesNoNoNo106.097194NoControlBilbao
211314Female72Former30.861060.654321NoYesNoYesNo85.946612NoMedDiet + VOOBilbao
311324Male71Former27.681180.694118YesNoYesNoNo82.907598YesMedDiet + NutsBilbao
411112Female79Never35.941290.806250YesNoYesNoNo94.761123NoMedDiet + VOOValencia
.........................................................
63191205Female66Never28.511040.645963YesNoYesYesNo83.550992NoControlMalaga
63201185Male80Never23.811090.589189YesYesYesYesNo82.743326NoControlMalaga
63213513Male57Former25.241000.571429YesNoYesNoNaN70.479124NoMedDiet + NutsBarcelona
63224995Female71Never32.04980.653333YesNoYesYesNo62.587269NoMedDiet + VOOMalaga
632312575Male58Former24.43930.547059YesYesYesNoNo92.590007NoMedDiet + NutsMalaga
\n", + "

6324 rows × 18 columns

\n", + "
" + ], + "text/plain": [ + " patient-id location-id sex age smoke bmi waist wth \\\n", + "0 436 4 Male 58 Former 33.53 122 0.753086 \n", + "1 1130 4 Male 77 Current 31.05 119 0.730061 \n", + "2 1131 4 Female 72 Former 30.86 106 0.654321 \n", + "3 1132 4 Male 71 Former 27.68 118 0.694118 \n", + "4 1111 2 Female 79 Never 35.94 129 0.806250 \n", + "... ... ... ... ... ... ... ... ... \n", + "6319 120 5 Female 66 Never 28.51 104 0.645963 \n", + "6320 118 5 Male 80 Never 23.81 109 0.589189 \n", + "6321 351 3 Male 57 Former 25.24 100 0.571429 \n", + "6322 499 5 Female 71 Never 32.04 98 0.653333 \n", + "6323 1257 5 Male 58 Former 24.43 93 0.547059 \n", + "\n", + " htn diab hyperchol famhist hormo p14 toevent event group \\\n", + "0 No No Yes No No 10 5.374401 Yes Control \n", + "1 Yes Yes No No No 10 6.097194 No Control \n", + "2 No Yes No Yes No 8 5.946612 No MedDiet + VOO \n", + "3 Yes No Yes No No 8 2.907598 Yes MedDiet + Nuts \n", + "4 Yes No Yes No No 9 4.761123 No MedDiet + VOO \n", + "... ... ... ... ... ... ... ... ... ... \n", + "6319 Yes No Yes Yes No 8 3.550992 No Control \n", + "6320 Yes Yes Yes Yes No 8 2.743326 No Control \n", + "6321 Yes No Yes No NaN 7 0.479124 No MedDiet + Nuts \n", + "6322 Yes No Yes Yes No 6 2.587269 No MedDiet + VOO \n", + "6323 Yes Yes Yes No No 9 2.590007 No MedDiet + Nuts \n", + "\n", + " City \n", + "0 Bilbao \n", + "1 Bilbao \n", + "2 Bilbao \n", + "3 Bilbao \n", + "4 Valencia \n", + "... ... \n", + "6319 Malaga \n", + "6320 Malaga \n", + "6321 Barcelona \n", + "6322 Malaga \n", + "6323 Malaga \n", + "\n", + "[6324 rows x 18 columns]" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "## your code here:\n" + "## your code here:\n", + "\n", + "df_location = df_merged.merge(locations, on = \"location-id\")\n", + "df_location\n", + "\n" ] }, { @@ -492,7 +1389,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 17, "id": "d1d4cc27", "metadata": {}, "outputs": [], @@ -502,7 +1399,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 18, "id": "fbebbd97", "metadata": {}, "outputs": [ @@ -512,7 +1409,7 @@ "(42, 2)" ] }, - "execution_count": 11, + "execution_count": 18, "metadata": {}, "output_type": "execute_result" } @@ -523,7 +1420,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 19, "id": "8a3c7943", "metadata": {}, "outputs": [ @@ -591,7 +1488,7 @@ "4 4 541" ] }, - "execution_count": 12, + "execution_count": 19, "metadata": {}, "output_type": "execute_result" } @@ -602,12 +1499,343 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 31, "id": "573687e7", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
patient-idlocation-idsexagesmokebmiwaistwthhtndiabhypercholfamhisthormop14toeventeventgroupCity
011Female77Never25.92940.657343YesNoYesYesNo95.538672NoMedDiet + VOOMadrid
121Female68Never34.851500.949367YesNoYesYesNaN103.063655NoMedDiet + NutsMadrid
231Female66Never37.501200.750000YesYesNoNoNo65.590691NoMedDiet + NutsMadrid
341Female77Never29.26930.628378YesYesNoNoNo65.456537NoMedDiet + VOOMadrid
451Female60Never30.021040.662420YesNoYesNoNo92.746064NoControlMadrid
.........................................................
631912535Male79Never25.281050.640244YesNoYesNoNo85.828884NoMedDiet + VOOMalaga
632012545Male62Former27.101040.594286YesNoYesYesNo95.067762NoMedDiet + NutsMalaga
632112555Female65Never35.021030.686667YesNoYesNoNo101.993155NoMedDiet + VOOMalaga
632212565Male61Never28.42940.576687YesYesNoNoNo92.039699NoMedDiet + NutsMalaga
632312575Male58Former24.43930.547059YesYesYesNoNo92.590007NoMedDiet + NutsMalaga
\n", + "

6282 rows × 18 columns

\n", + "
" + ], + "text/plain": [ + " patient-id location-id sex age smoke bmi waist wth \\\n", + "0 1 1 Female 77 Never 25.92 94 0.657343 \n", + "1 2 1 Female 68 Never 34.85 150 0.949367 \n", + "2 3 1 Female 66 Never 37.50 120 0.750000 \n", + "3 4 1 Female 77 Never 29.26 93 0.628378 \n", + "4 5 1 Female 60 Never 30.02 104 0.662420 \n", + "... ... ... ... ... ... ... ... ... \n", + "6319 1253 5 Male 79 Never 25.28 105 0.640244 \n", + "6320 1254 5 Male 62 Former 27.10 104 0.594286 \n", + "6321 1255 5 Female 65 Never 35.02 103 0.686667 \n", + "6322 1256 5 Male 61 Never 28.42 94 0.576687 \n", + "6323 1257 5 Male 58 Former 24.43 93 0.547059 \n", + "\n", + " htn diab hyperchol famhist hormo p14 toevent event group \\\n", + "0 Yes No Yes Yes No 9 5.538672 No MedDiet + VOO \n", + "1 Yes No Yes Yes NaN 10 3.063655 No MedDiet + Nuts \n", + "2 Yes Yes No No No 6 5.590691 No MedDiet + Nuts \n", + "3 Yes Yes No No No 6 5.456537 No MedDiet + VOO \n", + "4 Yes No Yes No No 9 2.746064 No Control \n", + "... ... ... ... ... ... ... ... ... ... \n", + "6319 Yes No Yes No No 8 5.828884 No MedDiet + VOO \n", + "6320 Yes No Yes Yes No 9 5.067762 No MedDiet + Nuts \n", + "6321 Yes No Yes No No 10 1.993155 No MedDiet + VOO \n", + "6322 Yes Yes No No No 9 2.039699 No MedDiet + Nuts \n", + "6323 Yes Yes Yes No No 9 2.590007 No MedDiet + Nuts \n", + "\n", + " City \n", + "0 Madrid \n", + "1 Madrid \n", + "2 Madrid \n", + "3 Madrid \n", + "4 Madrid \n", + "... ... \n", + "6319 Malaga \n", + "6320 Malaga \n", + "6321 Malaga \n", + "6322 Malaga \n", + "6323 Malaga \n", + "\n", + "[6282 rows x 18 columns]" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here\n" + "# your code here\n", + "\n", + "df_removed = df_location.merge(dropped, how = \"outer\", on = identifier, indicator = True)\n", + "\n", + "df_removed = df_removed.loc[df_removed[\"_merge\"] == \"left_only\",].drop([\"_merge\"], axis = 1)\n", + "df_removed" ] }, { @@ -622,14 +1850,16 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 32, "id": "85902eea", "metadata": {}, "outputs": [], "source": [ "fname = 'processed_data_predimed.csv'\n", "\n", - "# your code here\n" + "# your code here\n", + "\n", + "df_removed.to_csv(fname)\n" ] } ], @@ -649,7 +1879,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.5" + "version": "3.13.6" } }, "nbformat": 4, -- 2.39.5