From db5321e70d6ecf8a109b5802c32a1690beeb9529 Mon Sep 17 00:00:00 2001 From: unknown Date: Fri, 5 Mar 2021 16:41:43 +0100 Subject: [PATCH] function development added --- ...velopment of the function-checkpoint.ipynb | 1992 +++++++++++++++++ scripts/dev/development of the function.ipynb | 1992 +++++++++++++++++ 2 files changed, 3984 insertions(+) create mode 100644 scripts/dev/.ipynb_checkpoints/development of the function-checkpoint.ipynb create mode 100644 scripts/dev/development of the function.ipynb diff --git a/scripts/dev/.ipynb_checkpoints/development of the function-checkpoint.ipynb b/scripts/dev/.ipynb_checkpoints/development of the function-checkpoint.ipynb new file mode 100644 index 0000000..19a44a1 --- /dev/null +++ b/scripts/dev/.ipynb_checkpoints/development of the function-checkpoint.ipynb @@ -0,0 +1,1992 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import os\n", + "import numpy as np\n", + "import scipy as sp\n", + "from scipy import stats\n", + "from scipy.stats import pearsonr" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "How should be: \n", + "\n", + "Input: \n", + "- \"df\" the data in pandas df\n", + "- \"grouping vars\" the variables that we are grouping by, the order of them will determine the hierarchy in the table\n", + "- \"vars of interest\" the variables that will form the rows of the table" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### Loading data" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Current working directory is: C:\\Users\\katya\\MPI4\n" + ] + } + ], + "source": [ + "os.chdir(\"../../../\")\n", + "\n", + "# Checks current directory\n", + "cwd = os.getcwd() \n", + "print(\"Current working directory is:\", cwd) " + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "#Loading the data for session 1\n", + "\n", + "session1 = pd.read_csv('data/session1/clean_dataset.csv')\n", + "session1 = session1.set_index('PROLIFICID')" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "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", + "
submitdatelastpageSESSIONIDGROUPsr_agesr_gendersr_postcodeq6_me_infq6_close_person_infq6_close_person_died...stai_sasticsa_tasticsa_cog_tasticsa_som_tasticsa_sasticsa_cog_sasticsa_som_sabdicatPID
PROLIFICID
55d06fd334e9060012e5781c2020-04-17121.0UK32.0FME58UQ0.00.00.0...30.032.019.013.027.016.011.06.528.055d06fd334e9060012e5781c
563e35190980220011572d9a2020-04-17121.0UK26.0FS37GT1.01.00.0...39.025.014.011.028.016.012.012.033.0563e35190980220011572d9a
566ff4a3b937e400052d34892020-04-18121.0UK37.0FDE61JT0.00.00.0...39.032.019.013.033.020.013.010.023.0566ff4a3b937e400052d3489
56ca0400b30699000bd9d94f2020-04-17121.0UK39.0FPE0.00.00.0...30.024.012.012.021.010.011.01.014.056ca0400b30699000bd9d94f
57754d57ca706f000190eaf12020-04-17121.0UK34.0MRM94BL0.00.00.0...21.022.010.012.021.010.011.01.01.057754d57ca706f000190eaf1
\n", + "

5 rows × 86 columns

\n", + "
" + ], + "text/plain": [ + " submitdate lastpage SESSIONID GROUP sr_age \\\n", + "PROLIFICID \n", + "55d06fd334e9060012e5781c 2020-04-17 12 1.0 UK 32.0 \n", + "563e35190980220011572d9a 2020-04-17 12 1.0 UK 26.0 \n", + "566ff4a3b937e400052d3489 2020-04-18 12 1.0 UK 37.0 \n", + "56ca0400b30699000bd9d94f 2020-04-17 12 1.0 UK 39.0 \n", + "57754d57ca706f000190eaf1 2020-04-17 12 1.0 UK 34.0 \n", + "\n", + " sr_gender sr_postcode q6_me_inf \\\n", + "PROLIFICID \n", + "55d06fd334e9060012e5781c F ME58UQ 0.0 \n", + "563e35190980220011572d9a F S37GT 1.0 \n", + "566ff4a3b937e400052d3489 F DE61JT 0.0 \n", + "56ca0400b30699000bd9d94f F PE 0.0 \n", + "57754d57ca706f000190eaf1 M RM94BL 0.0 \n", + "\n", + " q6_close_person_inf q6_close_person_died ... \\\n", + "PROLIFICID ... \n", + "55d06fd334e9060012e5781c 0.0 0.0 ... \n", + "563e35190980220011572d9a 1.0 0.0 ... \n", + "566ff4a3b937e400052d3489 0.0 0.0 ... \n", + "56ca0400b30699000bd9d94f 0.0 0.0 ... \n", + "57754d57ca706f000190eaf1 0.0 0.0 ... \n", + "\n", + " stai_sa sticsa_ta sticsa_cog_ta sticsa_som_ta \\\n", + "PROLIFICID \n", + "55d06fd334e9060012e5781c 30.0 32.0 19.0 13.0 \n", + "563e35190980220011572d9a 39.0 25.0 14.0 11.0 \n", + "566ff4a3b937e400052d3489 39.0 32.0 19.0 13.0 \n", + "56ca0400b30699000bd9d94f 30.0 24.0 12.0 12.0 \n", + "57754d57ca706f000190eaf1 21.0 22.0 10.0 12.0 \n", + "\n", + " sticsa_sa sticsa_cog_sa sticsa_som_sa bdi cat \\\n", + "PROLIFICID \n", + "55d06fd334e9060012e5781c 27.0 16.0 11.0 6.5 28.0 \n", + "563e35190980220011572d9a 28.0 16.0 12.0 12.0 33.0 \n", + "566ff4a3b937e400052d3489 33.0 20.0 13.0 10.0 23.0 \n", + "56ca0400b30699000bd9d94f 21.0 10.0 11.0 1.0 14.0 \n", + "57754d57ca706f000190eaf1 21.0 10.0 11.0 1.0 1.0 \n", + "\n", + " PID \n", + "PROLIFICID \n", + "55d06fd334e9060012e5781c 55d06fd334e9060012e5781c \n", + "563e35190980220011572d9a 563e35190980220011572d9a \n", + "566ff4a3b937e400052d3489 566ff4a3b937e400052d3489 \n", + "56ca0400b30699000bd9d94f 56ca0400b30699000bd9d94f \n", + "57754d57ca706f000190eaf1 57754d57ca706f000190eaf1 \n", + "\n", + "[5 rows x 86 columns]" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "session1.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### Old Function " + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "def summary_table(session, round_val, round_val_p, name_to_save): \n", + " \n", + " '''\n", + " This function returns the data summary_table data frame. \n", + " \n", + " session = session number\n", + " round_val = hom many digits after dec point \n", + " round_val_p = how many digits after dec point for p-values\n", + " name_to_save = name that will be used for the output file and saved in xlsx\n", + " \n", + " \n", + " '''\n", + "\n", + " summary_table = pd.DataFrame({\n", + " \n", + " # Mean Values of Male Participants (Berlin Sample) \n", + " \n", + " ('Berlin', 'Male', 'M'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val)},\n", + " \n", + " # Gender Ratio (Berlin Sample)\n", + " \n", + " ('Berlin', 'Male', '%'): {\n", + " 'Gender Ratio': str(round((session['sr_gender'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].count() / session['sr_gender'][session['GROUP'] == 'BE'].count()) * 100,round_val)) + ' % ',\n", + " 'Age': '',\n", + " 'Trait Anxiety(STAIT)': '',\n", + " 'State Anxiety(STAIS)': '',\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': '',\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': '',\n", + " 'Beck Depression Inventory(BDI)':'',\n", + " 'Catastrophizing': ''}, \n", + " \n", + " # Male SD (Berlin Sample)\n", + " \n", + " ('Berlin', 'Male', 'SD'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val)}, \n", + " \n", + " # Mean Values of Female Participants (Berlin Sample) \n", + " \n", + " ('Berlin', 'Female', 'M'): {\n", + " 'Gender Ratio': '', \n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val)}, \n", + " \n", + " # Gender Ratio (Berlin Sample) \n", + " \n", + " ('Berlin', 'Female', '%'): {\n", + " 'Gender Ratio': str(round((session['sr_gender'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].count() / session['sr_gender'][session['GROUP'] == 'BE'].count()) * 100,round_val)) + ' %',\n", + " 'Age': '',\n", + " 'Trait Anxiety(STAIT)': '',\n", + " 'State Anxiety(STAIS)': '',\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': '',\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': '',\n", + " 'Beck Depression Inventory(BDI)':'',\n", + " 'Catastrophizing': ''}, \n", + " \n", + " # Female SD (Berlin Sample)\n", + " \n", + " ('Berlin', 'Female', 'SD'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Beck Depression Inventory(BDI)': round(session['bdi'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val)}, \n", + " \n", + " # p-values for Gender Groups (Berlin Sample)\n", + " \n", + " ('Berlin', '', 'P'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(stats.ttest_ind(session['sr_age'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['sr_age'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Anxiety(STAIT)': round(stats.ttest_ind(session['stai_ta'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['stai_ta'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'State Anxiety(STAIS)': round(stats.ttest_ind(session['stai_sa'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['stai_sa'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(stats.ttest_ind(session['sticsa_ta'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['sticsa_ta'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(stats.ttest_ind(session['sticsa_sa'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['sticsa_sa'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Beck Depression Inventory(BDI)':round(stats.ttest_ind(session['bdi'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['bdi'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Catastrophizing': round(stats.ttest_ind(session['cat'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['cat'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p)}, \n", + " \n", + " # Male Mean (UK Sample)\n", + " \n", + " ('UK', 'Male', 'M'): {\n", + " 'Gender Ratio': '', \n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val)}, \n", + " \n", + " # Gender Ratio for Males (UK Sample)\n", + " \n", + " ('UK', 'Male', '%'): {\n", + " 'Gender Ratio': str(round((session['sr_gender'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].count() / session['sr_gender'][session['GROUP'] == 'UK'].count()) * 100,round_val)) + ' %',\n", + " 'Age': '',\n", + " 'Trait Anxiety(STAIT)': '',\n", + " 'State Anxiety(STAIS)': '',\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': '',\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': '',\n", + " 'Beck Depression Inventory(BDI)':'',\n", + " 'Catastrophizing': ''},\n", + " \n", + " # Male SD (UK Sample)\n", + " \n", + " ('UK', 'Male', 'SD'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val)},\n", + " \n", + " # Female Mean (UK Sample)\n", + " \n", + " ('UK', 'Female', 'M'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val)}, \n", + " \n", + " # Gender Ratio for Females (UK Sample)\n", + " \n", + " ('UK', 'Female', '%'): {\n", + " 'Gender Ratio': str(round((session['sr_gender'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].count() / session['sr_gender'][session['GROUP'] == 'UK'].count()) * 100,round_val)) + ' %',\n", + " 'Age': '',\n", + " 'Trait Anxiety(STAIT)': '',\n", + " 'State Anxiety(STAIS)': '',\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': '',\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': '',\n", + " 'Beck Depression Inventory(BDI)':'',\n", + " 'Catastrophizing': ''}, \n", + " \n", + " # Female SD (UK Sample)\n", + " \n", + " ('UK', 'Female', 'SD'): {\n", + " 'Gender Ratio': '', \n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val)}, \n", + " \n", + " # p-values for Gender Groups (UK Sample)\n", + " \n", + " ('UK', '', 'P'): {\n", + " 'Gender Ratio': '', \n", + " 'Age': round(stats.ttest_ind(session['sr_age'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['sr_age'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Anxiety(STAIT)': round(stats.ttest_ind(session['stai_ta'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['stai_ta'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'State Anxiety(STAIS)': round(stats.ttest_ind(session['stai_sa'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['stai_sa'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(stats.ttest_ind(session['sticsa_ta'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['sticsa_ta'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(stats.ttest_ind(session['sticsa_sa'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['sticsa_sa'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Beck Depression Inventory(BDI)':round(stats.ttest_ind(session['bdi'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['bdi'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Catastrophizing': round(stats.ttest_ind(session['cat'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['cat'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p)}, \n", + " \n", + " # p-values for Counry Groups\n", + " \n", + " ('', 'P', ''): {\n", + " 'Gender Ratio': '', \n", + " 'Age': round(stats.ttest_ind(session['sr_age'][session['GROUP'] == 'BE'], session['sr_age'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Anxiety(STAIT)': round(stats.ttest_ind(session['stai_ta'][session['GROUP'] == 'BE'], session['stai_ta'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'State Anxiety(STAIS)': round(stats.ttest_ind(session['stai_sa'][session['GROUP'] == 'BE'], session['stai_sa'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(stats.ttest_ind(session['sticsa_ta'][session['GROUP'] == 'BE'], session['sticsa_ta'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(stats.ttest_ind(session['sticsa_sa'][session['GROUP'] == 'BE'], session['sticsa_sa'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'Beck Depression Inventory(BDI)':round(stats.ttest_ind(session['bdi'][session['GROUP'] == 'BE'], session['bdi'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'Catastrophizing': round(stats.ttest_ind(session['cat'][session['GROUP'] == 'BE'], session['cat'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p)}})\n", + " \n", + " summary_table.to_excel('output/' + name_to_save + '.xlsx') \n", + " return summary_table\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "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", + "
BerlinUK
MaleFemaleMaleFemaleP
M%SDM%SDPM%SDM%SDP
Gender Ratio36.36 %63.64 %39.29 %60.71 %
Age26.903.9626.504.960.69828.426.3827.546.010.2230.087
Trait Anxiety(STAIT)36.599.9442.3010.110.01245.7512.5748.2111.870.0840.000
State Anxiety(STAIS)32.0011.1438.3612.020.01639.0611.8943.8112.180.0010.000
Trait Cognitive and Somatic Anxiety (STICSAT)29.726.2435.459.810.00434.0110.8937.6611.300.0050.024
State Cognitive and Somatic Anxiety (STICSAS)27.097.2331.689.040.01632.1210.5134.3011.120.0880.006
Beck Depression Inventory(BDI)5.585.588.706.500.02512.259.9914.039.570.1170.000
Catastrophizing17.6210.7025.3814.470.01031.3316.9436.4016.550.0100.000
\n", + "
" + ], + "text/plain": [ + " Berlin \\\n", + " Male Female \n", + " M % SD M \n", + "Gender Ratio 36.36 % \n", + "Age 26.90 3.96 26.50 \n", + "Trait Anxiety(STAIT) 36.59 9.94 42.30 \n", + "State Anxiety(STAIS) 32.00 11.14 38.36 \n", + "Trait Cognitive and Somatic Anxiety (STICSAT) 29.72 6.24 35.45 \n", + "State Cognitive and Somatic Anxiety (STICSAS) 27.09 7.23 31.68 \n", + "Beck Depression Inventory(BDI) 5.58 5.58 8.70 \n", + "Catastrophizing 17.62 10.70 25.38 \n", + "\n", + " UK \\\n", + " Male \n", + " % SD P M \n", + "Gender Ratio 63.64 % \n", + "Age 4.96 0.698 28.42 \n", + "Trait Anxiety(STAIT) 10.11 0.012 45.75 \n", + "State Anxiety(STAIS) 12.02 0.016 39.06 \n", + "Trait Cognitive and Somatic Anxiety (STICSAT) 9.81 0.004 34.01 \n", + "State Cognitive and Somatic Anxiety (STICSAS) 9.04 0.016 32.12 \n", + "Beck Depression Inventory(BDI) 6.50 0.025 12.25 \n", + "Catastrophizing 14.47 0.010 31.33 \n", + "\n", + " \\\n", + " Female \n", + " % SD M % \n", + "Gender Ratio 39.29 % 60.71 % \n", + "Age 6.38 27.54 \n", + "Trait Anxiety(STAIT) 12.57 48.21 \n", + "State Anxiety(STAIS) 11.89 43.81 \n", + "Trait Cognitive and Somatic Anxiety (STICSAT) 10.89 37.66 \n", + "State Cognitive and Somatic Anxiety (STICSAS) 10.51 34.30 \n", + "Beck Depression Inventory(BDI) 9.99 14.03 \n", + "Catastrophizing 16.94 36.40 \n", + "\n", + " \n", + " P \n", + " SD P \n", + "Gender Ratio \n", + "Age 6.01 0.223 0.087 \n", + "Trait Anxiety(STAIT) 11.87 0.084 0.000 \n", + "State Anxiety(STAIS) 12.18 0.001 0.000 \n", + "Trait Cognitive and Somatic Anxiety (STICSAT) 11.30 0.005 0.024 \n", + "State Cognitive and Somatic Anxiety (STICSAS) 11.12 0.088 0.006 \n", + "Beck Depression Inventory(BDI) 9.57 0.117 0.000 \n", + "Catastrophizing 16.55 0.010 0.000 " + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "summary_table(session1, 2, 3, 'test')" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "session = session1" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Figuring out" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "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", + "
sr_agestai_tastai_sasticsa_tasticsa_sabdicat
GROUPsr_gender
BEF26.5042.3038.3635.4531.688.7025.38
M26.9036.5932.0029.7227.095.5817.62
UKF27.5448.2143.8137.6634.3014.0336.40
M28.4245.7539.0634.0132.1212.2531.33
\n", + "
" + ], + "text/plain": [ + " sr_age stai_ta stai_sa sticsa_ta sticsa_sa bdi cat\n", + "GROUP sr_gender \n", + "BE F 26.50 42.30 38.36 35.45 31.68 8.70 25.38\n", + " M 26.90 36.59 32.00 29.72 27.09 5.58 17.62\n", + "UK F 27.54 48.21 43.81 37.66 34.30 14.03 36.40\n", + " M 28.42 45.75 39.06 34.01 32.12 12.25 31.33" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "round(session.groupby(['GROUP',\"sr_gender\"])[[\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]].mean(),2)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "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", + "
sr_agestai_tastai_sasticsa_tasticsa_sabdicat
GROUPsr_gender
BEF4.9610.1112.029.819.046.5014.47
M3.969.9411.146.247.235.5810.70
UKF6.0111.8712.1811.3011.129.5716.55
M6.3812.5711.8910.8910.519.9916.94
\n", + "
" + ], + "text/plain": [ + " sr_age stai_ta stai_sa sticsa_ta sticsa_sa bdi cat\n", + "GROUP sr_gender \n", + "BE F 4.96 10.11 12.02 9.81 9.04 6.50 14.47\n", + " M 3.96 9.94 11.14 6.24 7.23 5.58 10.70\n", + "UK F 6.01 11.87 12.18 11.30 11.12 9.57 16.55\n", + " M 6.38 12.57 11.89 10.89 10.51 9.99 16.94" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "round(session.groupby(['GROUP',\"sr_gender\"])[[\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]].std(),2)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "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", + "
GROUPBEUK
sr_genderFMFM
sr_agestd4.963.966.016.38
mean26.5026.9027.5428.42
stai_tastd10.119.9411.8712.57
mean42.3036.5948.2145.75
stai_sastd12.0211.1412.1811.89
mean38.3632.0043.8139.06
sticsa_tastd9.816.2411.3010.89
mean35.4529.7237.6634.01
sticsa_sastd9.047.2311.1210.51
mean31.6827.0934.3032.12
bdistd6.505.589.579.99
mean8.705.5814.0312.25
catstd14.4710.7016.5516.94
mean25.3817.6236.4031.33
\n", + "
" + ], + "text/plain": [ + "GROUP BE UK \n", + "sr_gender F M F M\n", + "sr_age std 4.96 3.96 6.01 6.38\n", + " mean 26.50 26.90 27.54 28.42\n", + "stai_ta std 10.11 9.94 11.87 12.57\n", + " mean 42.30 36.59 48.21 45.75\n", + "stai_sa std 12.02 11.14 12.18 11.89\n", + " mean 38.36 32.00 43.81 39.06\n", + "sticsa_ta std 9.81 6.24 11.30 10.89\n", + " mean 35.45 29.72 37.66 34.01\n", + "sticsa_sa std 9.04 7.23 11.12 10.51\n", + " mean 31.68 27.09 34.30 32.12\n", + "bdi std 6.50 5.58 9.57 9.99\n", + " mean 8.70 5.58 14.03 12.25\n", + "cat std 14.47 10.70 16.55 16.94\n", + " mean 25.38 17.62 36.40 31.33" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = round(session.groupby(['GROUP',\"sr_gender\"])[[\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]].agg(['std', 'mean']),2)\n", + "df.transpose()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "_________________________________________________________________________________________________________________________________________________" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Function\n", + "\n", + "1. Figure out how to put p-values in there " + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We can pass the variables as lists" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "grouping_vars = ['GROUP',\"sr_gender\"]\n", + "vars_of_interest = [\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "a,b = session1[grouping_vars[0]].unique()" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "UK\n" + ] + } + ], + "source": [ + "print(a)" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "df_pval = round(session.groupby(grouping_vars)[vars_of_interest].agg(['std','mean']),2).transpose()" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "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", + "
GROUPBEUK
sr_genderFMFM
sr_agestd4.963.966.016.38
mean26.5026.9027.5428.42
stai_tastd10.119.9411.8712.57
mean42.3036.5948.2145.75
stai_sastd12.0211.1412.1811.89
mean38.3632.0043.8139.06
sticsa_tastd9.816.2411.3010.89
mean35.4529.7237.6634.01
sticsa_sastd9.047.2311.1210.51
mean31.6827.0934.3032.12
bdistd6.505.589.579.99
mean8.705.5814.0312.25
catstd14.4710.7016.5516.94
mean25.3817.6236.4031.33
\n", + "
" + ], + "text/plain": [ + "GROUP BE UK \n", + "sr_gender F M F M\n", + "sr_age std 4.96 3.96 6.01 6.38\n", + " mean 26.50 26.90 27.54 28.42\n", + "stai_ta std 10.11 9.94 11.87 12.57\n", + " mean 42.30 36.59 48.21 45.75\n", + "stai_sa std 12.02 11.14 12.18 11.89\n", + " mean 38.36 32.00 43.81 39.06\n", + "sticsa_ta std 9.81 6.24 11.30 10.89\n", + " mean 35.45 29.72 37.66 34.01\n", + "sticsa_sa std 9.04 7.23 11.12 10.51\n", + " mean 31.68 27.09 34.30 32.12\n", + "bdi std 6.50 5.58 9.57 9.99\n", + " mean 8.70 5.58 14.03 12.25\n", + "cat std 14.47 10.70 16.55 16.94\n", + " mean 25.38 17.62 36.40 31.33" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_pval" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "As function" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [], + "source": [ + "def summ_table(df, grouping_vars, vars_of_interest):\n", + " a,b = df[grouping_vars[0]].unique()\n", + " df = round(session.groupby(grouping_vars)[vars_of_interest].agg(['std', 'mean']),2)\n", + " return df.transpose()\n", + "\n", + "#when things will work I will put them here and change the view of the table" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "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", + "
GROUPBEUK
sr_genderFMFM
sr_agestd4.963.966.016.38
mean26.5026.9027.5428.42
stai_tastd10.119.9411.8712.57
mean42.3036.5948.2145.75
stai_sastd12.0211.1412.1811.89
mean38.3632.0043.8139.06
sticsa_tastd9.816.2411.3010.89
mean35.4529.7237.6634.01
sticsa_sastd9.047.2311.1210.51
mean31.6827.0934.3032.12
bdistd6.505.589.579.99
mean8.705.5814.0312.25
catstd14.4710.7016.5516.94
mean25.3817.6236.4031.33
\n", + "
" + ], + "text/plain": [ + "GROUP BE UK \n", + "sr_gender F M F M\n", + "sr_age std 4.96 3.96 6.01 6.38\n", + " mean 26.50 26.90 27.54 28.42\n", + "stai_ta std 10.11 9.94 11.87 12.57\n", + " mean 42.30 36.59 48.21 45.75\n", + "stai_sa std 12.02 11.14 12.18 11.89\n", + " mean 38.36 32.00 43.81 39.06\n", + "sticsa_ta std 9.81 6.24 11.30 10.89\n", + " mean 35.45 29.72 37.66 34.01\n", + "sticsa_sa std 9.04 7.23 11.12 10.51\n", + " mean 31.68 27.09 34.30 32.12\n", + "bdi std 6.50 5.58 9.57 9.99\n", + " mean 8.70 5.58 14.03 12.25\n", + "cat std 14.47 10.70 16.55 16.94\n", + " mean 25.38 17.62 36.40 31.33" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "summ_table(session, grouping_vars, vars_of_interest)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Playing around with columns' names /for later" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "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", + "
AgeSTAI Trait
GROUPsr_gender
BEF4.9626.5010.1142.3012.0238.369.8135.459.0431.686.508.7014.4725.38
M3.9626.909.9436.5911.1432.006.2429.727.2327.095.585.5810.7017.62
UKF6.0127.5411.8748.2112.1843.8111.3037.6611.1234.309.5714.0316.5536.40
M6.3828.4212.5745.7511.8939.0610.8934.0110.5132.129.9912.2516.9431.33
\n", + "
" + ], + "text/plain": [ + " Age STAI Trait \\\n", + "GROUP sr_gender \n", + "BE F 4.96 26.50 10.11 42.30 12.02 38.36 9.81 35.45 \n", + " M 3.96 26.90 9.94 36.59 11.14 32.00 6.24 29.72 \n", + "UK F 6.01 27.54 11.87 48.21 12.18 43.81 11.30 37.66 \n", + " M 6.38 28.42 12.57 45.75 11.89 39.06 10.89 34.01 \n", + "\n", + " \n", + "GROUP sr_gender \n", + "BE F 9.04 31.68 6.50 8.70 14.47 25.38 \n", + " M 7.23 27.09 5.58 5.58 10.70 17.62 \n", + "UK F 11.12 34.30 9.57 14.03 16.55 36.40 \n", + " M 10.51 32.12 9.99 12.25 16.94 31.33 " + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = round(session.groupby(['GROUP',\"sr_gender\"])[[\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]].agg(['std', 'mean']),2)\n", + "df.columns = ['Age', 'STAI Trait', '', '', '', '', '', '', '', '', '', '', '', '']\n", + "df" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Figuring out with p-value\n", + "\n", + "Here is the problem" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [], + "source": [ + "def ttest(x,y,sided=1):\n", + " return stats.ttest_ind(x, y, equal_var=False).pvalue/sided #function that calculates p-value" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "ename": "ValueError", + "evalue": "too many values to unpack (expected 2)", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 8\u001b[0m \u001b[1;31m# in order to calculate p-value we neeed to separate groups' values and here is the problem\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 9\u001b[0m \u001b[0ma\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mb\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'GROUP'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0munique\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 10\u001b[1;33m \u001b[0mc\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0md\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'sr_gender'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0munique\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 11\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 12\u001b[0m \u001b[0mdf_pval\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mround\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgroupby\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mgroupby\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mgender\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mvariables\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0magg\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'mean'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'std'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnan_policy\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'omit'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtranspose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mValueError\u001b[0m: too many values to unpack (expected 2)" + ] + } + ], + "source": [ + "df = session1\n", + "\n", + "group = 'GROUP'\n", + "gender = 'sr_gender'\n", + "variables = [\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]\n", + "\n", + "\n", + "# in order to calculate p-value we neeed to separate groups' values and here is the problem\n", + "a,b = df['GROUP'].unique()\n", + "c,d = df['sr_gender'].unique()\n", + " \n", + "df_pval = round(df.groupby([groupby,gender])[variables].agg(['mean','std'], nan_policy='omit'), 2).transpose()\n", + "\n", + "\n", + "df_pval['P-value'] = df.groupby(gender).apply(lambda dfx: get_ttest(\n", + " dfx.loc[dfx[group] == a, variables],\n", + " dfx.loc[dfx[group] == b, variables]))\n", + "\n", + "\n", + "df_pval" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "ename": "ValueError", + "evalue": "too many values to unpack (expected 2)", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mc\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0md\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msession\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'sr_gender'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0munique\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[1;31mValueError\u001b[0m: too many values to unpack (expected 2)" + ] + } + ], + "source": [ + "c,d = session['sr_gender'].unique()" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "UK\n", + "BE\n" + ] + } + ], + "source": [ + "a,b = df['GROUP'].unique()\n", + "print(a)\n", + "print(b)" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "count 396\n", + "unique 2\n", + "top F\n", + "freq 243\n", + "Name: sr_gender, dtype: object" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "session['sr_gender'].describe()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.4" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/scripts/dev/development of the function.ipynb b/scripts/dev/development of the function.ipynb new file mode 100644 index 0000000..19a44a1 --- /dev/null +++ b/scripts/dev/development of the function.ipynb @@ -0,0 +1,1992 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import os\n", + "import numpy as np\n", + "import scipy as sp\n", + "from scipy import stats\n", + "from scipy.stats import pearsonr" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "How should be: \n", + "\n", + "Input: \n", + "- \"df\" the data in pandas df\n", + "- \"grouping vars\" the variables that we are grouping by, the order of them will determine the hierarchy in the table\n", + "- \"vars of interest\" the variables that will form the rows of the table" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### Loading data" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Current working directory is: C:\\Users\\katya\\MPI4\n" + ] + } + ], + "source": [ + "os.chdir(\"../../../\")\n", + "\n", + "# Checks current directory\n", + "cwd = os.getcwd() \n", + "print(\"Current working directory is:\", cwd) " + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "#Loading the data for session 1\n", + "\n", + "session1 = pd.read_csv('data/session1/clean_dataset.csv')\n", + "session1 = session1.set_index('PROLIFICID')" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "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", + "
submitdatelastpageSESSIONIDGROUPsr_agesr_gendersr_postcodeq6_me_infq6_close_person_infq6_close_person_died...stai_sasticsa_tasticsa_cog_tasticsa_som_tasticsa_sasticsa_cog_sasticsa_som_sabdicatPID
PROLIFICID
55d06fd334e9060012e5781c2020-04-17121.0UK32.0FME58UQ0.00.00.0...30.032.019.013.027.016.011.06.528.055d06fd334e9060012e5781c
563e35190980220011572d9a2020-04-17121.0UK26.0FS37GT1.01.00.0...39.025.014.011.028.016.012.012.033.0563e35190980220011572d9a
566ff4a3b937e400052d34892020-04-18121.0UK37.0FDE61JT0.00.00.0...39.032.019.013.033.020.013.010.023.0566ff4a3b937e400052d3489
56ca0400b30699000bd9d94f2020-04-17121.0UK39.0FPE0.00.00.0...30.024.012.012.021.010.011.01.014.056ca0400b30699000bd9d94f
57754d57ca706f000190eaf12020-04-17121.0UK34.0MRM94BL0.00.00.0...21.022.010.012.021.010.011.01.01.057754d57ca706f000190eaf1
\n", + "

5 rows × 86 columns

\n", + "
" + ], + "text/plain": [ + " submitdate lastpage SESSIONID GROUP sr_age \\\n", + "PROLIFICID \n", + "55d06fd334e9060012e5781c 2020-04-17 12 1.0 UK 32.0 \n", + "563e35190980220011572d9a 2020-04-17 12 1.0 UK 26.0 \n", + "566ff4a3b937e400052d3489 2020-04-18 12 1.0 UK 37.0 \n", + "56ca0400b30699000bd9d94f 2020-04-17 12 1.0 UK 39.0 \n", + "57754d57ca706f000190eaf1 2020-04-17 12 1.0 UK 34.0 \n", + "\n", + " sr_gender sr_postcode q6_me_inf \\\n", + "PROLIFICID \n", + "55d06fd334e9060012e5781c F ME58UQ 0.0 \n", + "563e35190980220011572d9a F S37GT 1.0 \n", + "566ff4a3b937e400052d3489 F DE61JT 0.0 \n", + "56ca0400b30699000bd9d94f F PE 0.0 \n", + "57754d57ca706f000190eaf1 M RM94BL 0.0 \n", + "\n", + " q6_close_person_inf q6_close_person_died ... \\\n", + "PROLIFICID ... \n", + "55d06fd334e9060012e5781c 0.0 0.0 ... \n", + "563e35190980220011572d9a 1.0 0.0 ... \n", + "566ff4a3b937e400052d3489 0.0 0.0 ... \n", + "56ca0400b30699000bd9d94f 0.0 0.0 ... \n", + "57754d57ca706f000190eaf1 0.0 0.0 ... \n", + "\n", + " stai_sa sticsa_ta sticsa_cog_ta sticsa_som_ta \\\n", + "PROLIFICID \n", + "55d06fd334e9060012e5781c 30.0 32.0 19.0 13.0 \n", + "563e35190980220011572d9a 39.0 25.0 14.0 11.0 \n", + "566ff4a3b937e400052d3489 39.0 32.0 19.0 13.0 \n", + "56ca0400b30699000bd9d94f 30.0 24.0 12.0 12.0 \n", + "57754d57ca706f000190eaf1 21.0 22.0 10.0 12.0 \n", + "\n", + " sticsa_sa sticsa_cog_sa sticsa_som_sa bdi cat \\\n", + "PROLIFICID \n", + "55d06fd334e9060012e5781c 27.0 16.0 11.0 6.5 28.0 \n", + "563e35190980220011572d9a 28.0 16.0 12.0 12.0 33.0 \n", + "566ff4a3b937e400052d3489 33.0 20.0 13.0 10.0 23.0 \n", + "56ca0400b30699000bd9d94f 21.0 10.0 11.0 1.0 14.0 \n", + "57754d57ca706f000190eaf1 21.0 10.0 11.0 1.0 1.0 \n", + "\n", + " PID \n", + "PROLIFICID \n", + "55d06fd334e9060012e5781c 55d06fd334e9060012e5781c \n", + "563e35190980220011572d9a 563e35190980220011572d9a \n", + "566ff4a3b937e400052d3489 566ff4a3b937e400052d3489 \n", + "56ca0400b30699000bd9d94f 56ca0400b30699000bd9d94f \n", + "57754d57ca706f000190eaf1 57754d57ca706f000190eaf1 \n", + "\n", + "[5 rows x 86 columns]" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "session1.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### Old Function " + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "def summary_table(session, round_val, round_val_p, name_to_save): \n", + " \n", + " '''\n", + " This function returns the data summary_table data frame. \n", + " \n", + " session = session number\n", + " round_val = hom many digits after dec point \n", + " round_val_p = how many digits after dec point for p-values\n", + " name_to_save = name that will be used for the output file and saved in xlsx\n", + " \n", + " \n", + " '''\n", + "\n", + " summary_table = pd.DataFrame({\n", + " \n", + " # Mean Values of Male Participants (Berlin Sample) \n", + " \n", + " ('Berlin', 'Male', 'M'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].mean(),round_val)},\n", + " \n", + " # Gender Ratio (Berlin Sample)\n", + " \n", + " ('Berlin', 'Male', '%'): {\n", + " 'Gender Ratio': str(round((session['sr_gender'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].count() / session['sr_gender'][session['GROUP'] == 'BE'].count()) * 100,round_val)) + ' % ',\n", + " 'Age': '',\n", + " 'Trait Anxiety(STAIT)': '',\n", + " 'State Anxiety(STAIS)': '',\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': '',\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': '',\n", + " 'Beck Depression Inventory(BDI)':'',\n", + " 'Catastrophizing': ''}, \n", + " \n", + " # Male SD (Berlin Sample)\n", + " \n", + " ('Berlin', 'Male', 'SD'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'M'][session['GROUP'] == 'BE'].std(), round_val)}, \n", + " \n", + " # Mean Values of Female Participants (Berlin Sample) \n", + " \n", + " ('Berlin', 'Female', 'M'): {\n", + " 'Gender Ratio': '', \n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].mean(),round_val)}, \n", + " \n", + " # Gender Ratio (Berlin Sample) \n", + " \n", + " ('Berlin', 'Female', '%'): {\n", + " 'Gender Ratio': str(round((session['sr_gender'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].count() / session['sr_gender'][session['GROUP'] == 'BE'].count()) * 100,round_val)) + ' %',\n", + " 'Age': '',\n", + " 'Trait Anxiety(STAIT)': '',\n", + " 'State Anxiety(STAIS)': '',\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': '',\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': '',\n", + " 'Beck Depression Inventory(BDI)':'',\n", + " 'Catastrophizing': ''}, \n", + " \n", + " # Female SD (Berlin Sample)\n", + " \n", + " ('Berlin', 'Female', 'SD'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Beck Depression Inventory(BDI)': round(session['bdi'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'F'][session['GROUP'] == 'BE'].std(), round_val)}, \n", + " \n", + " # p-values for Gender Groups (Berlin Sample)\n", + " \n", + " ('Berlin', '', 'P'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(stats.ttest_ind(session['sr_age'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['sr_age'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Anxiety(STAIT)': round(stats.ttest_ind(session['stai_ta'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['stai_ta'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'State Anxiety(STAIS)': round(stats.ttest_ind(session['stai_sa'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['stai_sa'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(stats.ttest_ind(session['sticsa_ta'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['sticsa_ta'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(stats.ttest_ind(session['sticsa_sa'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['sticsa_sa'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Beck Depression Inventory(BDI)':round(stats.ttest_ind(session['bdi'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['bdi'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Catastrophizing': round(stats.ttest_ind(session['cat'][session['GROUP'] == 'BE'][session['sr_gender'] == 'M'], session['cat'][session['GROUP'] == 'BE'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p)}, \n", + " \n", + " # Male Mean (UK Sample)\n", + " \n", + " ('UK', 'Male', 'M'): {\n", + " 'Gender Ratio': '', \n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].mean(),round_val)}, \n", + " \n", + " # Gender Ratio for Males (UK Sample)\n", + " \n", + " ('UK', 'Male', '%'): {\n", + " 'Gender Ratio': str(round((session['sr_gender'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].count() / session['sr_gender'][session['GROUP'] == 'UK'].count()) * 100,round_val)) + ' %',\n", + " 'Age': '',\n", + " 'Trait Anxiety(STAIT)': '',\n", + " 'State Anxiety(STAIS)': '',\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': '',\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': '',\n", + " 'Beck Depression Inventory(BDI)':'',\n", + " 'Catastrophizing': ''},\n", + " \n", + " # Male SD (UK Sample)\n", + " \n", + " ('UK', 'Male', 'SD'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'M'][session['GROUP'] == 'UK'].std(), round_val)},\n", + " \n", + " # Female Mean (UK Sample)\n", + " \n", + " ('UK', 'Female', 'M'): {\n", + " 'Gender Ratio': '',\n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].mean(),round_val)}, \n", + " \n", + " # Gender Ratio for Females (UK Sample)\n", + " \n", + " ('UK', 'Female', '%'): {\n", + " 'Gender Ratio': str(round((session['sr_gender'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].count() / session['sr_gender'][session['GROUP'] == 'UK'].count()) * 100,round_val)) + ' %',\n", + " 'Age': '',\n", + " 'Trait Anxiety(STAIT)': '',\n", + " 'State Anxiety(STAIS)': '',\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': '',\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': '',\n", + " 'Beck Depression Inventory(BDI)':'',\n", + " 'Catastrophizing': ''}, \n", + " \n", + " # Female SD (UK Sample)\n", + " \n", + " ('UK', 'Female', 'SD'): {\n", + " 'Gender Ratio': '', \n", + " 'Age': round(session['sr_age'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Trait Anxiety(STAIT)': round(session['stai_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'State Anxiety(STAIS)': round(session['stai_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(session['sticsa_ta'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(session['sticsa_sa'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Beck Depression Inventory(BDI)':round(session['bdi'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val),\n", + " 'Catastrophizing': round(session['cat'][session['sr_gender'] == 'F'][session['GROUP'] == 'UK'].std(), round_val)}, \n", + " \n", + " # p-values for Gender Groups (UK Sample)\n", + " \n", + " ('UK', '', 'P'): {\n", + " 'Gender Ratio': '', \n", + " 'Age': round(stats.ttest_ind(session['sr_age'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['sr_age'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Anxiety(STAIT)': round(stats.ttest_ind(session['stai_ta'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['stai_ta'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'State Anxiety(STAIS)': round(stats.ttest_ind(session['stai_sa'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['stai_sa'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(stats.ttest_ind(session['sticsa_ta'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['sticsa_ta'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(stats.ttest_ind(session['sticsa_sa'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['sticsa_sa'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Beck Depression Inventory(BDI)':round(stats.ttest_ind(session['bdi'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['bdi'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p),\n", + " 'Catastrophizing': round(stats.ttest_ind(session['cat'][session['GROUP'] == 'UK'][session['sr_gender'] == 'M'], session['cat'][session['GROUP'] == 'UK'][session['sr_gender'] == 'F'], nan_policy='omit')[1], round_val_p)}, \n", + " \n", + " # p-values for Counry Groups\n", + " \n", + " ('', 'P', ''): {\n", + " 'Gender Ratio': '', \n", + " 'Age': round(stats.ttest_ind(session['sr_age'][session['GROUP'] == 'BE'], session['sr_age'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Anxiety(STAIT)': round(stats.ttest_ind(session['stai_ta'][session['GROUP'] == 'BE'], session['stai_ta'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'State Anxiety(STAIS)': round(stats.ttest_ind(session['stai_sa'][session['GROUP'] == 'BE'], session['stai_sa'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'Trait Cognitive and Somatic Anxiety (STICSAT)': round(stats.ttest_ind(session['sticsa_ta'][session['GROUP'] == 'BE'], session['sticsa_ta'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'State Cognitive and Somatic Anxiety (STICSAS)': round(stats.ttest_ind(session['sticsa_sa'][session['GROUP'] == 'BE'], session['sticsa_sa'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'Beck Depression Inventory(BDI)':round(stats.ttest_ind(session['bdi'][session['GROUP'] == 'BE'], session['bdi'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p),\n", + " 'Catastrophizing': round(stats.ttest_ind(session['cat'][session['GROUP'] == 'BE'], session['cat'][session['GROUP'] == 'UK'], nan_policy='omit')[1], round_val_p)}})\n", + " \n", + " summary_table.to_excel('output/' + name_to_save + '.xlsx') \n", + " return summary_table\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "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", + "
BerlinUK
MaleFemaleMaleFemaleP
M%SDM%SDPM%SDM%SDP
Gender Ratio36.36 %63.64 %39.29 %60.71 %
Age26.903.9626.504.960.69828.426.3827.546.010.2230.087
Trait Anxiety(STAIT)36.599.9442.3010.110.01245.7512.5748.2111.870.0840.000
State Anxiety(STAIS)32.0011.1438.3612.020.01639.0611.8943.8112.180.0010.000
Trait Cognitive and Somatic Anxiety (STICSAT)29.726.2435.459.810.00434.0110.8937.6611.300.0050.024
State Cognitive and Somatic Anxiety (STICSAS)27.097.2331.689.040.01632.1210.5134.3011.120.0880.006
Beck Depression Inventory(BDI)5.585.588.706.500.02512.259.9914.039.570.1170.000
Catastrophizing17.6210.7025.3814.470.01031.3316.9436.4016.550.0100.000
\n", + "
" + ], + "text/plain": [ + " Berlin \\\n", + " Male Female \n", + " M % SD M \n", + "Gender Ratio 36.36 % \n", + "Age 26.90 3.96 26.50 \n", + "Trait Anxiety(STAIT) 36.59 9.94 42.30 \n", + "State Anxiety(STAIS) 32.00 11.14 38.36 \n", + "Trait Cognitive and Somatic Anxiety (STICSAT) 29.72 6.24 35.45 \n", + "State Cognitive and Somatic Anxiety (STICSAS) 27.09 7.23 31.68 \n", + "Beck Depression Inventory(BDI) 5.58 5.58 8.70 \n", + "Catastrophizing 17.62 10.70 25.38 \n", + "\n", + " UK \\\n", + " Male \n", + " % SD P M \n", + "Gender Ratio 63.64 % \n", + "Age 4.96 0.698 28.42 \n", + "Trait Anxiety(STAIT) 10.11 0.012 45.75 \n", + "State Anxiety(STAIS) 12.02 0.016 39.06 \n", + "Trait Cognitive and Somatic Anxiety (STICSAT) 9.81 0.004 34.01 \n", + "State Cognitive and Somatic Anxiety (STICSAS) 9.04 0.016 32.12 \n", + "Beck Depression Inventory(BDI) 6.50 0.025 12.25 \n", + "Catastrophizing 14.47 0.010 31.33 \n", + "\n", + " \\\n", + " Female \n", + " % SD M % \n", + "Gender Ratio 39.29 % 60.71 % \n", + "Age 6.38 27.54 \n", + "Trait Anxiety(STAIT) 12.57 48.21 \n", + "State Anxiety(STAIS) 11.89 43.81 \n", + "Trait Cognitive and Somatic Anxiety (STICSAT) 10.89 37.66 \n", + "State Cognitive and Somatic Anxiety (STICSAS) 10.51 34.30 \n", + "Beck Depression Inventory(BDI) 9.99 14.03 \n", + "Catastrophizing 16.94 36.40 \n", + "\n", + " \n", + " P \n", + " SD P \n", + "Gender Ratio \n", + "Age 6.01 0.223 0.087 \n", + "Trait Anxiety(STAIT) 11.87 0.084 0.000 \n", + "State Anxiety(STAIS) 12.18 0.001 0.000 \n", + "Trait Cognitive and Somatic Anxiety (STICSAT) 11.30 0.005 0.024 \n", + "State Cognitive and Somatic Anxiety (STICSAS) 11.12 0.088 0.006 \n", + "Beck Depression Inventory(BDI) 9.57 0.117 0.000 \n", + "Catastrophizing 16.55 0.010 0.000 " + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "summary_table(session1, 2, 3, 'test')" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "session = session1" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Figuring out" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "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", + "
sr_agestai_tastai_sasticsa_tasticsa_sabdicat
GROUPsr_gender
BEF26.5042.3038.3635.4531.688.7025.38
M26.9036.5932.0029.7227.095.5817.62
UKF27.5448.2143.8137.6634.3014.0336.40
M28.4245.7539.0634.0132.1212.2531.33
\n", + "
" + ], + "text/plain": [ + " sr_age stai_ta stai_sa sticsa_ta sticsa_sa bdi cat\n", + "GROUP sr_gender \n", + "BE F 26.50 42.30 38.36 35.45 31.68 8.70 25.38\n", + " M 26.90 36.59 32.00 29.72 27.09 5.58 17.62\n", + "UK F 27.54 48.21 43.81 37.66 34.30 14.03 36.40\n", + " M 28.42 45.75 39.06 34.01 32.12 12.25 31.33" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "round(session.groupby(['GROUP',\"sr_gender\"])[[\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]].mean(),2)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "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", + "
sr_agestai_tastai_sasticsa_tasticsa_sabdicat
GROUPsr_gender
BEF4.9610.1112.029.819.046.5014.47
M3.969.9411.146.247.235.5810.70
UKF6.0111.8712.1811.3011.129.5716.55
M6.3812.5711.8910.8910.519.9916.94
\n", + "
" + ], + "text/plain": [ + " sr_age stai_ta stai_sa sticsa_ta sticsa_sa bdi cat\n", + "GROUP sr_gender \n", + "BE F 4.96 10.11 12.02 9.81 9.04 6.50 14.47\n", + " M 3.96 9.94 11.14 6.24 7.23 5.58 10.70\n", + "UK F 6.01 11.87 12.18 11.30 11.12 9.57 16.55\n", + " M 6.38 12.57 11.89 10.89 10.51 9.99 16.94" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "round(session.groupby(['GROUP',\"sr_gender\"])[[\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]].std(),2)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "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", + "
GROUPBEUK
sr_genderFMFM
sr_agestd4.963.966.016.38
mean26.5026.9027.5428.42
stai_tastd10.119.9411.8712.57
mean42.3036.5948.2145.75
stai_sastd12.0211.1412.1811.89
mean38.3632.0043.8139.06
sticsa_tastd9.816.2411.3010.89
mean35.4529.7237.6634.01
sticsa_sastd9.047.2311.1210.51
mean31.6827.0934.3032.12
bdistd6.505.589.579.99
mean8.705.5814.0312.25
catstd14.4710.7016.5516.94
mean25.3817.6236.4031.33
\n", + "
" + ], + "text/plain": [ + "GROUP BE UK \n", + "sr_gender F M F M\n", + "sr_age std 4.96 3.96 6.01 6.38\n", + " mean 26.50 26.90 27.54 28.42\n", + "stai_ta std 10.11 9.94 11.87 12.57\n", + " mean 42.30 36.59 48.21 45.75\n", + "stai_sa std 12.02 11.14 12.18 11.89\n", + " mean 38.36 32.00 43.81 39.06\n", + "sticsa_ta std 9.81 6.24 11.30 10.89\n", + " mean 35.45 29.72 37.66 34.01\n", + "sticsa_sa std 9.04 7.23 11.12 10.51\n", + " mean 31.68 27.09 34.30 32.12\n", + "bdi std 6.50 5.58 9.57 9.99\n", + " mean 8.70 5.58 14.03 12.25\n", + "cat std 14.47 10.70 16.55 16.94\n", + " mean 25.38 17.62 36.40 31.33" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = round(session.groupby(['GROUP',\"sr_gender\"])[[\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]].agg(['std', 'mean']),2)\n", + "df.transpose()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "_________________________________________________________________________________________________________________________________________________" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Function\n", + "\n", + "1. Figure out how to put p-values in there " + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We can pass the variables as lists" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "grouping_vars = ['GROUP',\"sr_gender\"]\n", + "vars_of_interest = [\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "a,b = session1[grouping_vars[0]].unique()" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "UK\n" + ] + } + ], + "source": [ + "print(a)" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "df_pval = round(session.groupby(grouping_vars)[vars_of_interest].agg(['std','mean']),2).transpose()" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "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", + "
GROUPBEUK
sr_genderFMFM
sr_agestd4.963.966.016.38
mean26.5026.9027.5428.42
stai_tastd10.119.9411.8712.57
mean42.3036.5948.2145.75
stai_sastd12.0211.1412.1811.89
mean38.3632.0043.8139.06
sticsa_tastd9.816.2411.3010.89
mean35.4529.7237.6634.01
sticsa_sastd9.047.2311.1210.51
mean31.6827.0934.3032.12
bdistd6.505.589.579.99
mean8.705.5814.0312.25
catstd14.4710.7016.5516.94
mean25.3817.6236.4031.33
\n", + "
" + ], + "text/plain": [ + "GROUP BE UK \n", + "sr_gender F M F M\n", + "sr_age std 4.96 3.96 6.01 6.38\n", + " mean 26.50 26.90 27.54 28.42\n", + "stai_ta std 10.11 9.94 11.87 12.57\n", + " mean 42.30 36.59 48.21 45.75\n", + "stai_sa std 12.02 11.14 12.18 11.89\n", + " mean 38.36 32.00 43.81 39.06\n", + "sticsa_ta std 9.81 6.24 11.30 10.89\n", + " mean 35.45 29.72 37.66 34.01\n", + "sticsa_sa std 9.04 7.23 11.12 10.51\n", + " mean 31.68 27.09 34.30 32.12\n", + "bdi std 6.50 5.58 9.57 9.99\n", + " mean 8.70 5.58 14.03 12.25\n", + "cat std 14.47 10.70 16.55 16.94\n", + " mean 25.38 17.62 36.40 31.33" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_pval" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "As function" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [], + "source": [ + "def summ_table(df, grouping_vars, vars_of_interest):\n", + " a,b = df[grouping_vars[0]].unique()\n", + " df = round(session.groupby(grouping_vars)[vars_of_interest].agg(['std', 'mean']),2)\n", + " return df.transpose()\n", + "\n", + "#when things will work I will put them here and change the view of the table" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "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", + "
GROUPBEUK
sr_genderFMFM
sr_agestd4.963.966.016.38
mean26.5026.9027.5428.42
stai_tastd10.119.9411.8712.57
mean42.3036.5948.2145.75
stai_sastd12.0211.1412.1811.89
mean38.3632.0043.8139.06
sticsa_tastd9.816.2411.3010.89
mean35.4529.7237.6634.01
sticsa_sastd9.047.2311.1210.51
mean31.6827.0934.3032.12
bdistd6.505.589.579.99
mean8.705.5814.0312.25
catstd14.4710.7016.5516.94
mean25.3817.6236.4031.33
\n", + "
" + ], + "text/plain": [ + "GROUP BE UK \n", + "sr_gender F M F M\n", + "sr_age std 4.96 3.96 6.01 6.38\n", + " mean 26.50 26.90 27.54 28.42\n", + "stai_ta std 10.11 9.94 11.87 12.57\n", + " mean 42.30 36.59 48.21 45.75\n", + "stai_sa std 12.02 11.14 12.18 11.89\n", + " mean 38.36 32.00 43.81 39.06\n", + "sticsa_ta std 9.81 6.24 11.30 10.89\n", + " mean 35.45 29.72 37.66 34.01\n", + "sticsa_sa std 9.04 7.23 11.12 10.51\n", + " mean 31.68 27.09 34.30 32.12\n", + "bdi std 6.50 5.58 9.57 9.99\n", + " mean 8.70 5.58 14.03 12.25\n", + "cat std 14.47 10.70 16.55 16.94\n", + " mean 25.38 17.62 36.40 31.33" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "summ_table(session, grouping_vars, vars_of_interest)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Playing around with columns' names /for later" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "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", + "
AgeSTAI Trait
GROUPsr_gender
BEF4.9626.5010.1142.3012.0238.369.8135.459.0431.686.508.7014.4725.38
M3.9626.909.9436.5911.1432.006.2429.727.2327.095.585.5810.7017.62
UKF6.0127.5411.8748.2112.1843.8111.3037.6611.1234.309.5714.0316.5536.40
M6.3828.4212.5745.7511.8939.0610.8934.0110.5132.129.9912.2516.9431.33
\n", + "
" + ], + "text/plain": [ + " Age STAI Trait \\\n", + "GROUP sr_gender \n", + "BE F 4.96 26.50 10.11 42.30 12.02 38.36 9.81 35.45 \n", + " M 3.96 26.90 9.94 36.59 11.14 32.00 6.24 29.72 \n", + "UK F 6.01 27.54 11.87 48.21 12.18 43.81 11.30 37.66 \n", + " M 6.38 28.42 12.57 45.75 11.89 39.06 10.89 34.01 \n", + "\n", + " \n", + "GROUP sr_gender \n", + "BE F 9.04 31.68 6.50 8.70 14.47 25.38 \n", + " M 7.23 27.09 5.58 5.58 10.70 17.62 \n", + "UK F 11.12 34.30 9.57 14.03 16.55 36.40 \n", + " M 10.51 32.12 9.99 12.25 16.94 31.33 " + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = round(session.groupby(['GROUP',\"sr_gender\"])[[\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]].agg(['std', 'mean']),2)\n", + "df.columns = ['Age', 'STAI Trait', '', '', '', '', '', '', '', '', '', '', '', '']\n", + "df" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Figuring out with p-value\n", + "\n", + "Here is the problem" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [], + "source": [ + "def ttest(x,y,sided=1):\n", + " return stats.ttest_ind(x, y, equal_var=False).pvalue/sided #function that calculates p-value" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "ename": "ValueError", + "evalue": "too many values to unpack (expected 2)", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 8\u001b[0m \u001b[1;31m# in order to calculate p-value we neeed to separate groups' values and here is the problem\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 9\u001b[0m \u001b[0ma\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mb\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'GROUP'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0munique\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 10\u001b[1;33m \u001b[0mc\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0md\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'sr_gender'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0munique\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 11\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 12\u001b[0m \u001b[0mdf_pval\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mround\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgroupby\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mgroupby\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mgender\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mvariables\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0magg\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'mean'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'std'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnan_policy\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'omit'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtranspose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mValueError\u001b[0m: too many values to unpack (expected 2)" + ] + } + ], + "source": [ + "df = session1\n", + "\n", + "group = 'GROUP'\n", + "gender = 'sr_gender'\n", + "variables = [\"sr_age\", \"stai_ta\", \"stai_sa\", \"sticsa_ta\", \"sticsa_sa\", \"bdi\", \"cat\"]\n", + "\n", + "\n", + "# in order to calculate p-value we neeed to separate groups' values and here is the problem\n", + "a,b = df['GROUP'].unique()\n", + "c,d = df['sr_gender'].unique()\n", + " \n", + "df_pval = round(df.groupby([groupby,gender])[variables].agg(['mean','std'], nan_policy='omit'), 2).transpose()\n", + "\n", + "\n", + "df_pval['P-value'] = df.groupby(gender).apply(lambda dfx: get_ttest(\n", + " dfx.loc[dfx[group] == a, variables],\n", + " dfx.loc[dfx[group] == b, variables]))\n", + "\n", + "\n", + "df_pval" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "ename": "ValueError", + "evalue": "too many values to unpack (expected 2)", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mc\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0md\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0msession\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'sr_gender'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0munique\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[1;31mValueError\u001b[0m: too many values to unpack (expected 2)" + ] + } + ], + "source": [ + "c,d = session['sr_gender'].unique()" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "UK\n", + "BE\n" + ] + } + ], + "source": [ + "a,b = df['GROUP'].unique()\n", + "print(a)\n", + "print(b)" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "count 396\n", + "unique 2\n", + "top F\n", + "freq 243\n", + "Name: sr_gender, dtype: object" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "session['sr_gender'].describe()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.4" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} -- GitLab