1  Descriptive Data Statistics

1.1 Python: Data Cleaning & Feature Engineering

1.1.1 Library imports

library(reticulate)
use_condaenv("dssg_env", required = TRUE)
py_config()

import pandas as pd
import os
from siuba import _, group_by, summarize, filter, select, mutate, arrange, count
import matplotlib.pyplot as plt

1.1.2 Data Import

youth = pd.read_csv('../../dssg-2025-mentor-canada/Data/Data_2020-Youth-Survey.csv')

1.1.3 Preview the first 6 rows and 7 columns.

youth.iloc[:6,:8]

           ResponseID DateCollected  ... geo_postcode_fsa  children_yesno
0  ECR-vlt6-982170254     11-Feb-20  ...              NaN               2
1  ECR-vlt6-625172748     11-Feb-20  ...              NaN               1
2  ECR-vlt6-416523871      8-Feb-20  ...              NaN               2
3  ECR-vlt6-933655693     11-Feb-20  ...              NaN               1
4  ECR-vlt6-780412096     11-Feb-20  ...              NaN               2
5  ECR-vlt6-197730841      6-Feb-20  ...              T2N               2

[6 rows x 8 columns]

youth.info()

<class ‘pandas.core.frame.DataFrame’> RangeIndex: 2838 entries, 0 to 2837 Columns: 737 entries, ResponseID to Age_5year dtypes: float64(389), int64(155), object(193) memory usage: 16.0+ MB

print(youth.shape)

(2838, 737)

null_counts = youth.isnull().sum()
null_counts = null_counts[null_counts > 0]

null_counts = null_counts.reset_index()
null_counts

                        index     0
0            geo_postcode_fsa  2250
1       income_ranged_dollar_  2250
2                  geo_ca_sac  2250
3    ethnicity_ca_14_oth1_1_1  2622
4    ethnicity_ca_14_oth1_2_2  2747
..                        ...   ...
530         QS1_17_INCARE_cat    16
531          QS4_5_SATEDU_cat   310
532     QS2_25_YOUTHINIT1_cat  1844
533               Arrival_age  2439
534           Arrival_age_cat  2439

[535 rows x 2 columns]

1.1.4 Reversing one-hot encoding for the gender identity column:

gender_cols = youth.loc[:,'QS1_9_GENDER1_1_1':'QS1_9_GENDER1_6_6']
youth['QS1_9_gender'] = gender_cols.idxmax(axis = 1)
youth['QS1_9_gender'].head().reset_index()

   index       QS1_9_gender
0      0  QS1_9_GENDER1_1_1
1      1  QS1_9_GENDER1_1_1
2      2  QS1_9_GENDER1_1_1
3      3  QS1_9_GENDER1_1_1
4      4  QS1_9_GENDER1_1_1

QS1_28_EMPLOYMENT_calculated, gender_cols

1.1.5 Create estimated total year income column:

(Feature engineering)

youth['yearly_from_month'] = youth['Month_income'].fillna(0) * 12
youth['yearly_from_seimimonth'] = youth['Semimonth_income'].fillna(0) * 24
youth['yearly_from_biweek'] = youth['Biweek_income'].fillna(0)*26
youth['yearly_from_week'] = youth['Week_income'].fillna(0) * 52

youth['total_yearly_income'] = (youth['yearly_from_month'] +
                                youth['yearly_from_seimimonth'] + 
                                youth['yearly_from_biweek'] + 
                                youth['yearly_from_week'])

1.1.5.1 Preview new total_yearly_income column:

(youth['total_yearly_income']).head()

0          0.0
1    1440000.0
2          0.0
3          0.0
4          0.0
Name: total_yearly_income, dtype: float64

1.1.5.2 Save manipulated dataset to local as an intermediate processed dataset:

youth.to_csv('../../dssg-2025-mentor-canada/Data/intermediate.csv')

1.2 R: Visualization

library(tidyverse)
library(knitr)
library(reticulate)

youth <- read_csv('../../dssg-2025-mentor-canada/Data/intermediate.csv')
kable(head(youth))

…1	ResponseID	DateCollected	TimeCollected	age	age_ranged_7_18_65	gender	geo_postcode_fsa	children_yesno	marital	employment	income_ranged_dollar_	geo_ca_region_8	geo_ca_province	geo_ca_sac	education_ca_9	ethnicity_ca_14_oth1_1_1	ethnicity_ca_14_oth1_2_2	ethnicity_ca_14_oth1_3_3	ethnicity_ca_14_oth1_4_4	ethnicity_ca_14_oth1_5_5	ethnicity_ca_14_oth1_6_6	ethnicity_ca_14_oth1_7_7	ethnicity_ca_14_oth1_8_8	ethnicity_ca_14_oth1_9_9	ethnicity_ca_14_oth1_10_10	ethnicity_ca_14_oth1_11_11	ethnicity_ca_14_oth1_12_12	ethnicity_ca_14_oth1_13_13	ethnicity_ca_14_oth1_14_14	ethnicity_ca_14_oth1_15_15	geo_postcode_UK	geo_uk_region_14	income_ranged_gbp_10_15k	employment_jobtype_uk_11	HH_SIZE	sample_flag	Country	ZipState	prName	Locale_Language	COUNTRY_PCZ	QS1_1_AGE	QAge_Validation	QS1_2_PROV	Logic_QS1_3_Ask	QS1_3_COMMUNITYTYPE	QS1_4_INDIGENOUS	QS1_5_INDIGENOUSHS	Logic_QS1_6_Qtext	Logic_Qtext	QS1_6_ETHNOCULTURAL1_1_1	QS1_6_ETHNOCULTURAL1_2_2	QS1_6_ETHNOCULTURAL1_3_3	QS1_6_ETHNOCULTURAL1_4_4	QS1_6_ETHNOCULTURAL1_5_5	QS1_6_ETHNOCULTURAL1_6_6	QS1_6_ETHNOCULTURAL1_7_7	QS1_6_ETHNOCULTURAL1_8_8	QS1_6_ETHNOCULTURAL1_9_9	QS1_6_ETHNOCULTURAL1_10_10	QS1_6_ETHNOCULTURAL1_11_11	QS1_6_ETHNOCULTURAL1_12_12	QS1_6_ETHNOCULTURAL1_13_13	QS1_6_ETHNOCULTURAL1_14_14	QS1_6_Other	QS1_7_NEWCOMER	QS1_8_NEWCOMERYEAR	QS1_8_Validation	QS1_9_GENDER1_1_1	QS1_9_GENDER1_2_2	QS1_9_GENDER1_3_3	QS1_9_GENDER1_4_4	QS1_9_GENDER1_5_5	QS1_9_GENDER1_6_6	QS1_9_Other	QS1_10_TRANSUM	QS1_11_SEXUALO	QS1_11_Other	QS1_12_DISABIL	QS1_13_DISABIL	QS1_14_DISABIL	Logic_QS1_15_A	QS1_15_DISABIL	QS1_16_PRIMARY1_1_1	QS1_16_PRIMARY1_2_2	QS1_16_PRIMARY1_3_3	QS1_16_PRIMARY1_4_4	QS1_16_PRIMARY1_5_5	QS1_16_PRIMARY1_6_6	QS1_16_PRIMARY1_7_7	QS1_16_PRIMARY1_8_8	QS1_16_PRIMARY1_9_9	QS1_16_PRIMARY1_10_10	QS1_16_PRIMARY1_11_11	QS1_16_PRIMARY1_12_12	QS1_16_PRIMARY1_13_13	QS1_16_Other	QS1_17_INCARE	QS1_18_PARENTEDUC1	QS1_18_Other_1	QS1_18_PARENTEDUC2	QS1_18_Other_2	QS1_18_PARENTEDUC3	QS1_18_Other_3	QS1_18_PARENTEDUC4	QS1_18_Other_4	QS1_18_PARENTEDUC5	QS1_18_Other_5	QS1_18_PARENTEDUC6	QS1_18_Other_6	QS1_18_PARENTEDUC7	QS1_18_Other_7	QS1_18_PARENTEDUC8	QS1_18_Other_8	QS1_18_PARENTEDUC9	QS1_18_Other_9	QS1_18_PARENTEDUC10	QS1_18_Other_10	QS1_18_PARENTEDUC11	QS1_18_Other_11	QS1_19_HIGHSCHOOL	QS1_20_HIGHSCHOOL	QS1_21_FURTHEDUCA	QS1_22_HIGHESTEDU	QS1_22_Other	QS1_23_YEARCOMPLE	QS1_25_EMPLOYMENT	Logic_QS1_26_Ask	QS1_26_EMPLOYMENT	QS1_26_Other	QS1_27_PLANNINGRE	QS1_27_Other	QS1_28_EMPLOYMENT	QS1_29_EMPLOYMENT	QS1_29_Validation	QS1_30_EMPLOYMENT1	QS1_30_MValidatio	QS1_30_EMPLOYMENT2	QS1_30_SMValidati	QS1_31_EMPLOYMENT	QS1_31_BWValidati	QS1_32_WEEKLY	QS1_32_WValidatio	QS2_1_MEANINGFULP	QS2_2_MEANINGFULP	QS2_3_PRESENCEOFM	QS2_4_MENTOR61FOR	QS2_5_MENTOR611PR	QS2_5_Other	QS2_6_MENTOREXPER	QS2_7_MENTOR611SE	QS2_8_UNMETNEED61	QS2_9_PRESENCEOFA	QS2_10_NUMBEROFME	QS2_10_Validation	QS2_11_MENTOR1218	QS2_12_UNMETNEED1	Logic_QS2_14_Ask	QS2_13_ACCESSBARR1_1_1	QS2_13_ACCESSBARR1_2_2	QS2_13_ACCESSBARR1_3_3	QS2_13_ACCESSBARR1_4_4	QS2_13_ACCESSBARR1_5_5	QS2_13_ACCESSBARR1_6_6	QS2_13_ACCESSBARR1_7_7	QS2_13_ACCESSBARR1_8_8	QS2_13_ACCESSBARR1_9_9	QS2_13_ACCESSBARR1_10_10	QS2_13_ACCESSBARR1_11_11	QS2_13_Other	QS2_14_MENTORID	QS2_14_MENTORID_2	QS2_14_MENTORID_3	Logic_MENTORID1_1_1	Logic_MENTORID1_2_2	Logic_MENTORID1_3_3	QS2_15_RELATIONS1_1_1	QS2_15_RELATIONS1_2_2	QS2_15_RELATIONS1_3_3	QS2_15_RELATIONS1_4_4	QS2_15_RELATIONS1_5_5	QS2_15_RELATIONS1_6_6	QS2_15_RELATIONS1_7_7	QS2_15_RELATIONS1_8_8	QS2_15_RELATIONS1_9_9	QS2_15_RELATIONS1_10_10	QS2_15_RELATIONS1_11_11	QS2_15_RELATIONS1_12_12	QS2_15_RELATIONS1_13_13	QS2_15_RELATIONS1_14_14	QS2_15_RELATIONS1_15_15	QS2_15_RELATIONSHIP1	QS2_16_FORMAT_1	QS2_17_TYPE_1	QS2_17_TYPE_1_Other	QS2_18_LOCATION_1	QS2_18_LOCATION_1_O	QS2_19_DURATION_1	QS2_20_EXPERIENCE_1	QS2_21_FOCUS_11_1_1	QS2_21_FOCUS_11_2_2	QS2_21_FOCUS_11_3_3	QS2_22_GEOLOCATI1	QS2_15_RELATIONS2_1_1	QS2_15_RELATIONS2_2_2	QS2_15_RELATIONS2_3_3	QS2_15_RELATIONS2_4_4	QS2_15_RELATIONS2_5_5	QS2_15_RELATIONS2_6_6	QS2_15_RELATIONS2_7_7	QS2_15_RELATIONS2_8_8	QS2_15_RELATIONS2_9_9	QS2_15_RELATIONS2_10_10	QS2_15_RELATIONS2_11_11	QS2_15_RELATIONS2_12_12	QS2_15_RELATIONS2_13_13	QS2_15_RELATIONS2_14_14	QS2_15_RELATIONS2_15_15	QS2_15_RELATIONSHIP2	QS2_16_FORMAT_2	QS2_17_TYPE_2	QS2_17_TYPE_2_Other	QS2_18_LOCATION_2	QS2_18_LOCATION_2_O	QS2_19_DURATION_2	QS2_20_EXPERIENCE_2	QS2_21_FOCUS_21_1_1	QS2_21_FOCUS_21_2_2	QS2_21_FOCUS_21_3_3	QS2_22_GEOLOCATI2	QS2_15_RELATIONS3_1_1	QS2_15_RELATIONS3_2_2	QS2_15_RELATIONS3_3_3	QS2_15_RELATIONS3_4_4	QS2_15_RELATIONS3_5_5	QS2_15_RELATIONS3_6_6	QS2_15_RELATIONS3_7_7	QS2_15_RELATIONS3_8_8	QS2_15_RELATIONS3_9_9	QS2_15_RELATIONS3_10_10	QS2_15_RELATIONS3_11_11	QS2_15_RELATIONS3_12_12	QS2_15_RELATIONS3_13_13	QS2_15_RELATIONS3_14_14	QS2_15_RELATIONS3_15_15	QS2_15_RELATIONSHIP3	QS2_16_FORMAT_3	QS2_17_TYPE_3	QS2_17_TYPE_3_Other	QS2_18_LOCATION_3	QS2_18_LOCATION_3_O	QS2_19_DURATION_3	QS2_20_EXPERIENCE_3	QS2_21_FOCUS_31_1_1	QS2_21_FOCUS_31_2_2	QS2_21_FOCUS_31_3_3	QS2_22_GEOLOCATI3	Logic_AP_QS2_23	QS2_23_MOSTMEANI	QS2_24_MENTORAGE	QS2_25_YOUTHINIT1	QS2_25_YOUTHINIT2	QS2_26_INITIATIO1_1_1	QS2_26_INITIATIO1_2_2	QS2_26_INITIATIO1_3_3	QS2_26_INITIATIO1_4_4	QS2_26_INITIATIO1_5_5	QS2_26_INITIATIO1_6_6	QS2_26_INITIATIO1_7_7	QS2_26_INITIATIO1_8_8	QS2_26_INITIATIO1_9_9	QS2_26_INITIATIO1_10_10	QS2_26_INITIATIO1_11_11	QS2_26_INITIATIO1_12_12	QS2_26_INITIATIO1_13_13	QS2_26_INITIATIO1_14_14	QS2_26_INITIATIO1_15_15	QS2_26_INITIATIO1_16_16	QS2_26_INITIATIO1_17_17	QS2_26_INITIATIONEV	Logic_QS2_27_Ask	QS2_27_MENTORPROGRA1	QS2_27_MENTORPROGRA2	QS2_28_MATCHCHOICE	QS2_29_MATCHCRITERI1_1_1	QS2_29_MATCHCRITERI1_2_2	QS2_29_MATCHCRITERI1_3_3	QS2_29_MATCHCRITERI1_4_4	QS2_29_MATCHCRITERI1_5_5	QS2_29_MATCHCRITERI1_6_6	QS2_29_MATCHCRITERI1_7_7	QS2_29_MATCHCRITERI1_8_8	QS2_29_MATCHCRITERI1_9_9	QS2_29_MATCHCRITERI1_10_10	QS2_29_MATCHCRITERI1_11_11	QS2_29_MATCHCRITERIA_O	QS2_30_MATCHSIMILAR1_1_1	QS2_30_MATCHSIMILAR1_2_2	QS2_30_MATCHSIMILAR1_3_3	QS2_30_MATCHSIMILAR1_4_4	QS2_30_MATCHSIMILAR1_5_5	QS2_31_MENTORINGREL1_1_1	QS2_31_MENTORINGREL1_2_2	QS2_31_MENTORINGREL1_3_3	QS2_31_MENTORINGREL1_4_4	QS2_31_MENTORINGREL1_5_5	QS2_32_MENTORINGENG1_1_1	QS2_32_MENTORINGENG1_2_2	QS2_32_MENTORINGENG1_3_3	QS2_32_MENTORINGENG1_4_4	QS2_32_MENTORINGENG1_5_5	QS2_32_MENTORINGENG1_6_6	QS2_32_MENTORINGENG1_7_7	QS2_32_MENTORINGENG1_8_8	QS2_32_MENTORINGENG1_9_9	QS2_32_MENTORINGENG1_10_10	QS2_32_MENTORINGENG1_11_11	QS2_32_MENTORINGENG1_12_12	QS2_32_MENTORINGENG1_13_13	QS2_32_MENTORINGENG1_14_14	QS2_32_MENTORINGENG1_15_15	QS2_32_MENTORINGENG1_16_16	QS2_32_MENTORINGENG1_17_17	QS2_32_MENTORINGENG1_18_18	QS2_32_MENTORINGENG1_19_19	QS2_32_MENTORINGENG1_20_20	QS2_32_MENTORINGENG1_21_21	QS2_32_MENTORINGENG1_22_22	QS2_33_TRANSITIONS1_1_1	QS2_33_TRANSITIONS1_2_2	QS2_33_TRANSITIONS1_3_3	QS2_33_TRANSITIONS1_4_4	QS2_33_TRANSITIONS1_5_5	QS2_33_TRANSITIONS1_6_6	QS2_33_TRANSITIONS1_7_7	QS2_33_TRANSITIONS1_8_8	QS2_33_TRANSITIONS1_9_9	QS2_33_TRANSITIONS1_10_10	QS2_33_TRANSITIONS1_11_11	QS2_33_TRANSITIONS1_12_12	QS2_33_TRANSITIONS1_13_13	QS2_33_TRANSITIONS1_14_14	QS2_33_TRANSITIONS_Ot	QS2_34_SUPPORTS1_1_1	QS2_34_SUPPORTS1_2_2	QS2_34_SUPPORTS1_3_3	QS2_34_SUPPORTS1_4_4	QS2_34_SUPPORTS1_5_5	QS2_34_SUPPORTS1_6_6	QS2_34_SUPPORTS1_7_7	QS2_34_SUPPORTS1_8_8	QS2_34_SUPPORTS1_9_9	QS2_34_SUPPORTS1_10_10	QS2_34_SUPPORTS_Ot	Logic_QS2_34_Valid	Logic_QS2_35_Ask	Logic_QS2_35_Mask1_1_1	Logic_QS2_35_Mask1_2_2	Logic_QS2_35_Mask1_3_3	Logic_QS2_35_Mask1_4_4	Logic_QS2_35_Mask1_5_5	Logic_QS2_35_Mask1_6_6	Logic_QS2_35_Mask1_7_7	Logic_QS2_35_Mask1_8_8	Logic_QS2_35_Mask1_9_9	Logic_QS2_35_Mask1_10_10	QS2_35_SUPPORTSIMPO1_1_1	QS2_35_SUPPORTSIMPO1_2_2	QS2_35_SUPPORTSIMPO1_3_3	QS2_35_SUPPORTSIMPO1_4_4	QS2_35_SUPPORTSIMPO1_5_5	QS2_35_SUPPORTSIMPO1_6_6	QS2_35_SUPPORTSIMPO1_7_7	QS2_35_SUPPORTSIMPO1_8_8	QS2_35_SUPPORTSIMPO1_9_9	QS2_35_SUPPORTSIMPO1_10_10	QS2_36_INFLUENCE1_1_1	QS2_36_INFLUENCE1_2_2	QS2_36_INFLUENCE1_3_3	QS2_36_INFLUENCE1_4_4	QS2_36_INFLUENCE1_5_5	QS2_36_INFLUENCE1_6_6	QS2_36_INFLUENCE1_7_7	QS2_36_INFLUENCE1_8_8	QS2_36_INFLUENCE1_9_9	QS2_37_HELPFULNESS	QS2_38_NETGATIVEME1_1_1	QS2_38_NETGATIVEME1_2_2	QS2_38_NETGATIVEME1_3_3	QS2_38_NETGATIVEME1_4_4	QS2_38_NETGATIVEME1_5_5	QS2_38_NETGATIVEME1_6_6	QS2_38_NETGATIVEME1_7_7	QS2_38_NETGATIVEME1_8_8	QS2_38_NETGATIVEME1_9_9	QS2_38_NETGATIVEME1_10_10	QS2_38_NETGATIVEME1_11_11	QS2_38_NETGATIVEME1_12_12	QS2_38_NETGATIVEME1_13_13	QS2_38_NETGATIVEME1_14_14	QS2_38_NETGATIVEME1_15_15	QS2_38_NETGATIVEME1_16_16	QS2_38_NETGATIVEME1_17_17	QS2_38_NETGATIVEME1_18_18	QS2_38_NETGATIVEME1_19_19	QS2_38_NETGATIVEMENTO	QS2_39_NEGATIVEMENT1_1_1	QS2_39_NEGATIVEMENT1_2_2	QS2_39_NEGATIVEMENT1_3_3	QS2_39_NEGATIVEMENT1_4_4	QS2_39_NEGATIVEMENT1_5_5	QS2_39_NEGATIVEMENT1_6_6	QS2_39_NEGATIVEMENT1_7_7	QS2_39_NEGATIVEMENT1_8_8	QS2_39_NEGATIVEMENT1_9_9	QS2_39_NEGATIVEMENT1_10_10	QS2_39_NEGATIVEMENT1_11_11	QS2_39_NEGATIVEMENT1_12_12	QS2_39_NEGATIVEMENT1_13_13	QS2_39_NEGATIVEMENT1_14_14	QS2_39_NEGATIVEMENT1_15_15	QS2_39_NEGATIVEMENT1_16_16	QS2_39_NEGATIVEMENT1_17_17	QS2_39_NEGATIVEMENT1_18_18	QS2_39_NEGATIVEMENT1_19_19	QS2_39_1_Other	QS_40_REMATCHING_1	QS2_39_NEGATIVEMENT2_1_1	QS2_39_NEGATIVEMENT2_2_2	QS2_39_NEGATIVEMENT2_3_3	QS2_39_NEGATIVEMENT2_4_4	QS2_39_NEGATIVEMENT2_5_5	QS2_39_NEGATIVEMENT2_6_6	QS2_39_NEGATIVEMENT2_7_7	QS2_39_NEGATIVEMENT2_8_8	QS2_39_NEGATIVEMENT2_9_9	QS2_39_NEGATIVEMENT2_10_10	QS2_39_NEGATIVEMENT2_11_11	QS2_39_NEGATIVEMENT2_12_12	QS2_39_NEGATIVEMENT2_13_13	QS2_39_NEGATIVEMENT2_14_14	QS2_39_NEGATIVEMENT2_15_15	QS2_39_NEGATIVEMENT2_16_16	QS2_39_NEGATIVEMENT2_17_17	QS2_39_NEGATIVEMENT2_18_18	QS2_39_NEGATIVEMENT2_19_19	QS2_39_2_Other	QS_40_REMATCHING_2	QS2_39_NEGATIVEMENT3_1_1	QS2_39_NEGATIVEMENT3_2_2	QS2_39_NEGATIVEMENT3_3_3	QS2_39_NEGATIVEMENT3_4_4	QS2_39_NEGATIVEMENT3_5_5	QS2_39_NEGATIVEMENT3_6_6	QS2_39_NEGATIVEMENT3_7_7	QS2_39_NEGATIVEMENT3_8_8	QS2_39_NEGATIVEMENT3_9_9	QS2_39_NEGATIVEMENT3_10_10	QS2_39_NEGATIVEMENT3_11_11	QS2_39_NEGATIVEMENT3_12_12	QS2_39_NEGATIVEMENT3_13_13	QS2_39_NEGATIVEMENT3_14_14	QS2_39_NEGATIVEMENT3_15_15	QS2_39_NEGATIVEMENT3_16_16	QS2_39_NEGATIVEMENT3_17_17	QS2_39_NEGATIVEMENT3_18_18	QS2_39_NEGATIVEMENT3_19_19	QS2_39_3_Other	QS_40_REMATCHING_3	QS3_1_GLOBALSELFWOR1_1_1	QS3_1_GLOBALSELFWOR1_2_2	QS3_1_GLOBALSELFWOR1_3_3	QS3_1_GLOBALSELFWOR1_4_4	QS3_1_GLOBALSELFWOR1_5_5	QS3_1_GLOBALSELFWOR1_6_6	QS3_1_GLOBALSELFWOR1_7_7	QS3_1_GLOBALSELFWOR1_8_8	QS3_2_TRANSITIONWIT1_1_1	QS3_2_TRANSITIONWIT1_2_2	QS3_2_TRANSITIONWIT1_3_3	QS3_2_TRANSITIONWIT1_4_4	QS3_2_TRANSITIONWIT1_5_5	QS3_2_TRANSITIONWIT1_6_6	QS3_2_TRANSITIONWIT1_7_7	QS3_2_TRANSITIONWIT1_8_8	QS3_2_TRANSITIONWIT1_9_9	QS3_2_TRANSITIONWIT1_10_10	QS3_2_TRANSITIONWIT1_11_11	QS3_2_TRANSITIONWIT1_12_12	QS3_2_TRANSITIONWIT1_13_13	QS3_2_TRANSITIONWITHOUTMEN	QS3_3_TRANSITIONSWI1_1_1	QS3_3_TRANSITIONSWI1_2_2	QS3_3_TRANSITIONSWI1_3_3	QS3_3_TRANSITIONSWI1_4_4	QS3_3_TRANSITIONSWI1_5_5	QS3_3_TRANSITIONSWI1_6_6	QS3_3_TRANSITIONSWI1_7_7	QS3_3_TRANSITIONSWI1_8_8	QS3_3_TRANSITIONSWI1_9_9	QS3_3_TRANSITIONSWI1_10_10	QS3_3_TRANSITIONSWI1_11_11	QS3_3_TRANSITIONSWI1_12_12	QS3_3_TRANSITIONSWI1_13_13	QS3_3_TRANSITIONSWI1_14_14	QS3_3_TRANSITIONSWI1_15_15	QS3_3_TRANSITIONSWI1_16_16	QS3_3_TRANSITIONSWI1_17_17	QS3_3_TRANSITIONSWITHOUTMENTO	QS3_4_LIFEEVENTS1_1_1	QS3_4_LIFEEVENTS1_2_2	QS3_4_LIFEEVENTS1_3_3	QS3_4_LIFEEVENTS1_4_4	QS3_4_LIFEEVENTS1_5_5	QS3_4_LIFEEVENTS1_6_6	QS3_4_LIFEEVENTS1_7_7	QS3_4_LIFEEVENTS1_8_8	QS3_4_LIFEEVENTS1_9_9	QS3_4_LIFEEVENTS1_10_10	QS3_4_LIFEEVENTS1_11_11	QS3_4_LIFEEVENTS1_12_12	QS3_4_LIFEEVENTS1_13_13	QS3_4_LIFEEVENTS1_14_14	QS3_4_LIFEEVENTS1_15_15	QS3_4_LIFEEVENTS1_16_16	QS3_4_LIFEEVENTS1_17_17	QS3_4_LIFEEVENTS1_18_18	QS3_4_LIFEEVENTS1_19_19	QS3_4_LIFEEVENTS1_20_20	QS3_5_SCHOOLCLIMATE1_1_1	QS3_5_SCHOOLCLIMATE1_2_2	QS3_5_SCHOOLCLIMATE1_3_3	QS3_5_SCHOOLCLIMATE1_4_4	QS3_5_SCHOOLCLIMATE1_5_5	QS3_5_SCHOOLCLIMATE1_6_6	QS3_5_SCHOOLCLIMATE1_7_7	QS3_5_SCHOOLCLIMATE1_8_8	QS3_5_SCHOOLCLIMATE1_9_9	QS3_5_SCHOOLCLIMATE1_10_10	QS4_1_MEANINGFULPERSON	QS4_2_MEANINGFULPERSON	QS4_3_CAREERPLANNIN1_1_1	QS4_3_CAREERPLANNIN1_2_2	QS4_3_CAREERPLANNIN1_3_3	QS4_3_CAREERPLANNIN1_4_4	QS4_3_CAREERPLANNIN1_5_5	QS4_3_CAREERPLANNIN1_6_6	QS4_3_CAREERPLANNIN1_7_7	QS4_3_CAREERPLANNIN1_8_8	QS4_4_EDUCATIONALEXPEC	QS4_4_Other	QS4_5_SATEDU	QS4_5_SATEDU_Other	QS4_6_DISAPPOINTED	QS4_7_SOCIALCAPITAL1_1_1	QS4_7_SOCIALCAPITAL1_2_2	QS4_7_SOCIALCAPITAL1_3_3	QS4_7_SOCIALCAPITAL1_4_4	QS4_8_HELPSEEKING1_1_1	QS4_8_HELPSEEKING1_2_2	QS4_8_HELPSEEKING1_3_3	QS4_8_HELPSEEKING1_4_4	QS4_8_HELPSEEKING1_5_5	QS4_8_HELPSEEKING1_6_6	QS4_8_HELPSEEKING1_7_7	QS4_8_HELPSEEKING1_8_8	QS4_8_HELPSEEKING1_9_9	QS4_8_HELPSEEKING1_10_10	QS4_9_MENTALHEALTH	QS4_10_MENTALWELLBE1_1_1	QS4_10_MENTALWELLBE1_2_2	QS4_10_MENTALWELLBE1_3_3	QS4_10_MENTALWELLBE1_4_4	QS4_10_MENTALWELLBE1_5_5	QS4_10_MENTALWELLBE1_6_6	QS4_10_MENTALWELLBE1_7_7	QS4_11_BELONGING	QS4_12_TRUST1_1_1	QS4_12_TRUST1_2_2	QS4_12_TRUST1_3_3	QS4_12_TRUST1_4_4	QS4_12_TRUST1_5_5	QS4_13_LIFEEVE1_1_1	QS4_13_LIFEEVE1_2_2	QS4_13_LIFEEVE1_3_3	QS4_13_LIFEEVE1_4_4	QS4_13_LIFEEVE1_5_5	QS4_13_LIFEEVE1_6_6	QS4_14_FORMALVOL	QS4_14_Validatio	QS4_15_TIMEIFFOR1	QS4_15_TIMEIFFOR2	QS4_15_TIMEIFFOR3	QS4_15_TIMEIFFOR4	QS4_15_Validatio	QS4_16_FORMALVOL	QS4_17_SERVEDASM	QS4_18_CURRENTOR	QS4_19_CURRENTME1	QS4_19_CURRENTME2	QS4_19_CURRENTME3	QS4_19_Validatio	QS4_20_MENTEEAGE	QS4_21_MENTORING	QS4_22_PASTMENTO	QS4_23_PASTFORMA1	QS4_23_PASTFORMA2	QS4_23_PASTFORMA3	QS4_23_Validatio	QS4_23_MENTEEAGE	QS4_24_FUTUREMEN	QS4_25_FUTUREMEN	QS4_26_INTERNETC	QS4_27_INTERNETC1_1_1	QS4_27_INTERNETC1_2_2	QS4_27_INTERNETC1_3_3	QS4_27_INTERNETC1_4_4	QS4_28_INTERNETCON	QS4_29_PRIVATECONN	QS4_30_INTERNETCON	QS4_31_MOBILECONNE	QS4_32_MOBILECONNE1_1_1	QS4_32_MOBILECONNE1_2_2	QS4_32_MOBILECONNE1_3_3	QS4_32_MOBILECONNE1_4_4	QS4_33_MOBILECONNECT	QS1_8_NEWCOMERYEAR_cat	QS2_10_NUMBEROFME_cat	Global_selfworth_total	Future_interest_mentor	Q38_LIFEEVENTS_1	Q38_LIFEEVENTS_2	Q38_LIFEEVENTS_3	Q38_LIFEEVENTS_4	Q38_LIFEEVENTS_5	Q38_LIFEEVENTS_6	Q38_LIFEEVENTS_7	Q38_LIFEEVENTS_8	Q38_LIFEEVENTS_9	Q38_LIFEEVENTS_10	Q38_LIFEEVENTS_11	Q38_LIFEEVENTS_12	Q38_LIFEEVENTS_13	Q38_LIFEEVENTS_14	Q38_LIFEEVENTS_15	Q38_LIFEEVENTS_16	Q38_LIFEEVENTS_17	Q38_LIFEEVENTS_18	Q38_LIFEEVENTS_19	Q38_LIFEEVENTS_20	Q49_LIFEEVENTS_1	Q49_LIFEEVENTS_2	Q49_LIFEEVENTS_3	Q49_LIFEEVENTS_4	Q49_LIFEEVENTS_5	Q49_LIFEEVENTS_6	QS1_4_INDIGENOUS_cat	QS1_6_ETHNOCULTURAL1_cat	Q49_LIFEEVENTS_Riskfactors	Q49_LIFEEVENTS_Riskfactors_cat	Q38_Risk_factors	Q38_Risk_factors_cat	QS1_9_GENDER1_cat	Mentor_Age12	sexo_straight	QS1_11_SEXUALO_cat	QS1_22_HIGHESTEDU_cat	QS1_25_EMPLOYMENT_cat	QS4_9_MENTALHEALTH_cat	QS4_11_BELONGING_cat	QS1_12_DISABIL_cat	QS1_13_DISABIL_cat	QS1_19_HIGHSCHOOL_cat	QS1_21_FURTHEDUC_cat	QS1_3_COMMUNITYTYPE_cat	QS1_3_COMMUNITYTYPE_cat2	QS2_1_MEANINGFULP_cat	QS2_2_MEANINGFULP_cat	QS2_3_PRESENCEOFM_cat	QS2_4_MENTOR61FOR_cat	QS2_6_MENTOREXPER_cat	QS4_17_SERVEDASM_cat	QS4_18_CURRENTOR_cat	QS4_25_FUTUREMEN_cat	QS4_24_FUTUREMEN_cat	QS1_7_NEWCOMER_cat	Month_income	Semimonth_income	Biweek_income	Week_income	QS1_28_EMPLOYMENT_calculated	QS2_16_FORMAT_any	Anymentor_ages618	Anyformalm_ages618	QS2_8_UNMETNEED61_cat	QS2_12_UNMETNEED1_cat	QS1_10_TRANSUM_cat	QS2_20_EXPERIENCE_mostmeaningful	QS2_20_EXPERIENCE_cat	QS4_3_CAREERPLANNIN1_total	QS4_7_SOCIALCAPITAL1_total	QS2_16_FORMAT_mostmeaningful	Any_unmetneed_6to18	Q_RELATIONSHIP1_mostmeaningful	Q_RELATIONSHIP2_mostmeaningful	Q_RELATIONSHIP3_mostmeaningful	Q_RELATIONSHIP4_mostmeaningful	Q_RELATIONSHIP5_mostmeaningful	Q_RELATIONSHIP6_mostmeaningful	Q_RELATIONSHIP7_mostmeaningful	Q_RELATIONSHIP8_mostmeaningful	Q_RELATIONSHIP9_mostmeaningful	Q_RELATIONSHIP10_mostmeaningful	Q_RELATIONSHIP11_mostmeaningful	Q_RELATIONSHIP12_mostmeaningful	Q_RELATIONSHIP13_mostmeaningful	Q_RELATIONSHIP14_mostmeaningful	QS2_17_TYPE_mostmeaningful	QS2_18_LOCATION_mostmeaningful	QS2_19_DURATION_mostmeaningful	Q_FOCUS1_mostmeaningful	Q_FOCUS2_mostmeaningful	Q_FOCUS3_mostmeaningful	Q_GEOLOCAT_mostmeaningful	QS1_17_INCARE_cat	QS4_5_SATEDU_cat	Q46_MENTALWELLBEING_total	QS2_25_YOUTHINIT1_cat	Age_2year	Age_census_year	Q38_Risk_factors_cat2	QS1_1_AGE_cat	Birth_year	Arrival_age	Arrival_age_cat	Immigrant_exclude	Age_5year	QS1_9_gender	yearly_from_month	yearly_from_seimimonth	yearly_from_biweek	yearly_from_week	total_yearly_income
0	ECR-vlt6-982170254	11-Feb-20	05:25:00	21	2	2	NA	2	1	3	NA	2	1	NA	3	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	1	NA	NA	en_US	NA	21	1	Alberta	1	Urban	I don’t identify as a member of these communities	NA	You may belong to one or more racial or cultural groups on the following list Check all that apply	1	0	0	0	0	0	0	0	0	0	0	0	0	0	1	NA	Yes	NA	NA	1	0	0	0	0	0	NA	No	Heterosexual	NA	No	NA	NA	NA	NA	1	1	0	0	0	0	0	0	0	0	0	0	0	NA	NA	5	NA	9	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	Yes	14	Yes	Other, please specify:	still in university	2019	Studying or in education/training	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	Yes	Yes	Unsure	NA	NA	NA	NA	2	Yes	Yes	3	1	NA	No	1	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	shsh	sh	mm	1	1	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	NA	No	1	NA	2	NA	4	2	1	0	1	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	NA	No	1	NA	2	NA	3	3	0	0	1	1	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	NA	No	1	NA	2	NA	5	2	1	1	1	1	NA	1	3-5 years older than me	Someone else put us in touch	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	3	2	3	3	2	4	4	4	4	4	3	3	3	3	3	3	3	3	3	3	3	3	3	3	3	3	3	3	3	3	3	3	No	Yes	No	No	No	No	No	No	Yes	Yes	No	No	No	No	NA	Very true	Very true	Very true	Very true	Very true	Very true	Very true	Very true	Very true	3	he supported me	1	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	4	4	4	4	4	4	4	4	4	4	A lot	A lot	A lot	A lot	A lot	A lot	A lot	A lot	A lot	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	4	1	4	4	1	4	4	1	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	4	3	NA	Unsure	Unsure	Unsure	Unsure	Unsure	Unsure	Unsure	Unsure	NA	NA	University diploma or certificate BELOW Bachelor’s Degree	NA	1	Neutral	Neutral	Neutral	Neutral	3	3	3	3	3	3	3	3	3	3	Good	3	3	3	3	3	3	3	Somewhat strong	3	3	3	3	3	2	2	2	2	2	2	1	1	100	NA	NA	NA	1	1	No	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	Fairly interested	Both	1	1	1	0	0	2	1	NA	1	1	1	0	0	1	NA	1 to 5	23	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	Not Indigenous	NA	0	No Risk factors	0	No Risk factors	Woman	Yes mentor	NA	Heterosexual	NA	Studying and/ or working	Good/ Excellent	Strong/ somewhat strong	No	NA	Yes	Yes	Urban/Sub	1	Yes	Yes	NA	NA	NA	No	NA	Formal or both	Very/ Fairly interested	Yes	NA	NA	NA	NA	NA	No	Yes	No	Yes	No	No	Mostly positive	Positive experience	32	12	No	Yes	0	0	1	0	0	0	0	0	0	0	0	0	0	0	One-on-one	In community	12+ months	1	0	1	Yes	No	Some university or more	21	Non-youth initiated	21 to 22	2	0 or 1 risk factor	18-21	1999	NA	NA	Not immigrant or <=18 at arrival	18 to 24	QS1_9_GENDER1_1_1	0	0	0	0	0
1	ECR-vlt6-625172748	11-Feb-20	10:53:00	22	2	2	NA	1	1	1	NA	5	9	NA	9	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	1	NA	NA	en_US	NA	22	1	Ontario	1	Suburban	Métis	1	You may also belong to one or more racial or cultural groups on the following list Check all that apply	2	0	0	0	0	0	0	0	0	0	0	1	0	0	0	NA	Yes	NA	NA	1	0	0	0	0	0	NA	No	Asexual	NA	Yes	No	13	1	9	1	1	0	0	0	0	0	0	1	0	0	0	0	NA	NA	5	NA	4	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	9	NA	NA	NA	NA	NA	Yes	9	Yes	University diploma or certificate BELOW Bachelor’s Degree	NA	2019	Working (paid work for at least 1 hr/week)	NA	NA	NA	NA	NA	Monthly	NA	NA	10000	1	NA	NA	NA	NA	NA	NA	Yes	No	Yes	No	NA	NA	Always positive	NA	Yes	No	NA	NA	1	Yes	2	1	1	0	0	0	1	0	0	0	0	0	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	1	3	3	3	2	2	1	1	0	0	1	0	0	0	1	0	1	0	0	0	0	NA	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	NA	1	1	3	2	1	2	1	2	1	2	2	1	3	3	1	2	2	2	1	2	1	2	2	2	3	1	2	3	3	3	3	NA	Agree	Somewhat agree	Agree	Somewhat agree	Somewhat disagree	Somewhat agree	Somewhat agree	Agree	NA	NA	Master’s degree (e.g. M.B.A., M.A., M.Sc.)	NA	1	Disagree	Agree	Disagree	Strongly Agree	3	4	5	1	2	5	2	3	2	3	Good	1	2	4	2	3	5	3	Somewhat weak	2	2	3	1	3	1	2	2	2	2	3	1	1	NA	NA	1	NA	1	2	Yes, and I am currently a mentor	Informal	NA	NA	NA	NA	Under 18 years old	1	NA	NA	NA	NA	NA	NA	Fairly interested	Both	1	1	1	0	0	1	1	NA	1	1	1	0	0	3	NA	NA	16	1	1	1	0	0	1	0	1	0	1	0	0	1	0	0	1	0	0	0	1	0	1	0	0	0	0	0	Indigenous	White only	1	1 or more risk factors	6	1 or more risk factors	Woman	No mentor	NA	Other	Some university or more	Studying and/ or working	Good/ Excellent	Weak/ somewhat weak	Yes	No	Yes	Yes	Urban/Sub	1	Yes	No	Yes	No	Positive experience	Yes	Informal only	Formal or both	Very/ Fairly interested	Yes	120000	NA	NA	NA	120000	NA	Yes	No	Yes	Yes	No	NA	NA	41	13	NA	Yes	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	No	Some university or more	20	NA	21 to 22	2	2 or more risk ractors	22-25	1998	NA	NA	Not immigrant or <=18 at arrival	18 to 24	QS1_9_GENDER1_1_1	1440000	0	0	0	1440000
2	ECR-vlt6-416523871	8-Feb-20	46:03:00	22	2	1	NA	2	5	3	NA	7	6	NA	4	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	1	NA	NA	en_US	NA	21	1	Yukon	1	Remote	First Nations (North American Indian)	4	You may also belong to one or more racial or cultural groups on the following list Check all that apply	2	0	0	0	0	0	0	0	0	0	0	1	0	0	0	NA	Prefer not to answer	NA	NA	1	0	0	0	0	0	NA	Prefer not to answer	Gay	NA	No	NA	NA	NA	NA	0	0	0	0	1	0	0	0	0	0	0	0	0	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	8	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	Prefer not to answer	NA	No	NA	NA	NA	Studying or in education/training	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	No	Unsure	No	NA	NA	NA	NA	1	Unsure	No	NA	NA	3	No	2	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	3	3	1	4	1	4	4	1	1	0	0	0	0	0	0	0	0	0	0	0	0	NA	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	NA	1	2	3	2	4	2	1	1	1	2	1	4	3	3	3	1	1	1	2	1	1	1	4	3	1	2	1	2	1	1	1	1	Agree	Somewhat agree	Unsure	Disagree	Completely disagree	Agree	Completely agree	Completely agree	NA	NA	Certificate of Apprenticeship or Certificate of Qualification	NA	3	Strongly disagree	Strongly Agree	Strongly disagree	Neutral	1	5	5	1	3	2	2	5	1	4	Excellent	1	1	2	2	5	3	5	Don’t know	1	3	1	4	5	1	2	2	1	4	3	0	1	NA	NA	NA	NA	NA	NA	Yes, and I am currently a mentor	Formal	NA	0	1	1	Unsure	1	NA	NA	NA	NA	NA	NA	Fairly interested	Both	3	NA	NA	NA	NA	NA	NA	NA	4	NA	NA	NA	NA	NA	NA	NA	21	1	1	0	0	0	0	0	1	1	1	0	1	0	0	0	0	1	1	1	0	1	1	0	0	1	0	0	Indigenous	White only	2	1 or more risk factors	6	1 or more risk factors	Woman	No mentor	NA	Other	NA	Studying and/ or working	Good/ Excellent	NA	No	NA	NA	No	Rural/remote	3	No	NA	No	NA	NA	Yes	Formal or both	Formal or both	Very/ Fairly interested	NA	NA	NA	NA	NA	NA	NA	No	NA	NA	No	NA	NA	NA	38	10	NA	No	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	No	Less than University	19	NA	21 to 22	2	2 or more risk ractors	18-21	1999	NA	NA	Not immigrant or <=18 at arrival	18 to 24	QS1_9_GENDER1_1_1	0	0	0	0	0
3	ECR-vlt6-933655693	11-Feb-20	30:28:00	18	2	2	NA	1	1	2	NA	1	2	NA	3	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	1	NA	NA	en_US	NA	18	1	British Columbia	1	Urban	I don’t identify as a member of these communities	NA	You may belong to one or more racial or cultural groups on the following list Check all that apply	1	0	0	0	0	0	0	0	0	0	0	1	0	0	0	NA	No	2018	1	1	0	0	0	0	0	NA	No	Bisexual, pansexual, or queer	NA	Yes	Yes	15	1	17	1	1	0	0	0	0	0	0	0	0	0	0	0	NA	NA	9	NA	11	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	Yes	17	Yes	Unsure	NA	2019	Neither of the above	NA	1	NA	1	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	No	Yes	No	NA	NA	NA	NA	2	No	Yes	1	1	NA	No	1	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	bark	NA	NA	1	NA	NA	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	NA	No	2	NA	2	NA	4	2	1	0	0	2	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	1	1	More than 6 years older than me	Someone else put us in touch	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	3	3	3	2	1	5	3	2	3	5	3	3	1	1	3	3	3	3	2	1	1	3	3	3	3	3	3	3	3	1	2	3	Yes	No	Yes	No	No	No	No	No	No	No	No	No	No	No	NA	Not very true	Very true	Very true	Not very true	Not very true	Very true	Very true	Sometimes true	Not very true	2	na	1	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	4	4	4	4	4	4	4	4	4	4	A little	Some	A lot	A lot	A little	A lot	A lot	Quite a bit	Some	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	4	3	2	1	4	4	4	1	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	1	2	2	1	2	2	1	1	2	2	2	2	2	2	2	2	2	2	2	1	1	1	1	1	3	3	1	1	2	3	3	NA	Completely disagree	Completely agree	Completely disagree	Completely disagree	Completely agree	Disagree	Completely disagree	Completely disagree	5	NA	University diploma or certificate BELOW Bachelor’s Degree	NA	2	Disagree	Strongly Agree	Strongly Agree	Strongly Agree	3	4	1	2	1	5	1	5	2	2	Fair	2	2	2	1	2	5	5	Somewhat weak	1	3	5	2	3	2	2	2	1	2	2	1	1	6	NA	NA	NA	1	2	No	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	Not that interested	Informal	1	1	1	0	0	1	2	NA	1	1	1	0	0	1	2016 to 2020	1 to 5	23	2	1	0	0	1	0	0	1	1	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	1	0	0	Not Indigenous	White only	1	1 or more risk factors	2	1 or more risk factors	Woman	Yes mentor	NA	Other	NA	Not in employ or edu	Poor or fair	Weak/ somewhat weak	Yes	Yes	Yes	Yes	Urban/Sub	1	No	Yes	No	NA	NA	No	NA	Informal only	Not interested	No	NA	NA	NA	NA	NA	No	Yes	No	No	No	No	Mostly positive	Positive experience	21	17	No	No	0	0	0	0	0	0	0	0	0	0	0	0	0	1	With other youth	In community	12+ months	1	0	0	No	No	Some university or more	19	Non-youth initiated	18 to 20	1	2 or more risk ractors	18-21	2002	16	12-18	Not immigrant or <=18 at arrival	18 to 24	QS1_9_GENDER1_1_1	0	0	0	0	0
4	ECR-vlt6-780412096	11-Feb-20	35:51:00	24	2	2	NA	2	1	1	NA	2	1	NA	7	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	1	NA	NA	en_US	NA	23	1	Alberta	1	Suburban	I don’t identify as a member of these communities	NA	You may belong to one or more racial or cultural groups on the following list Check all that apply	1	0	0	0	0	0	0	0	0	0	0	1	0	0	0	NA	Yes	NA	NA	1	0	0	0	0	0	NA	No	Heterosexual	NA	No	NA	NA	NA	NA	1	1	0	0	0	0	0	0	0	0	0	0	0	NA	NA	9	NA	11	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	Yes	5	Yes	Bachelor’s degree (e.g. BA, BSc, B.Ed., B.Eng including LL.B-law degree)	NA	2017	Working (paid work for at least 1 hr/week)	NA	NA	NA	NA	NA	Yearly	89000	1	NA	NA	NA	NA	NA	NA	NA	NA	Unsure	Yes	Unsure	NA	NA	NA	NA	3	No	Unsure	NA	NA	3	Unsure	2	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	3	3	3	3	4	3	3	3	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	1	2	2	1	2	2	2	1	2	1	2	2	2	2	1	2	2	2	2	2	3	2	2	2	2	2	2	2	3	3	2	2	Agree	Agree	Agree	Agree	Agree	Agree	Agree	Agree	NA	NA	Master’s degree (e.g. M.B.A., M.A., M.Sc.)	NA	1	Agree	Agree	Agree	Agree	4	3	3	3	3	3	3	3	3	3	Excellent	3	4	4	4	4	3	5	Somewhat strong	5	3	3	1	3	2	2	2	2	2	2	2	1	24	NA	NA	NA	1	3	Yes, I have been a mentor but am not currently a mentor	NA	NA	NA	NA	NA	NA	2	2	NA	NA	NA	NA	1	Fairly interested	Unsure	1	0	0	1	0	NA	NA	NA	2	NA	NA	NA	NA	NA	NA	NA	25	1	1	0	0	1	0	0	0	1	0	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	Not Indigenous	White only	0	No Risk factors	1	1 or more risk factors	Woman	NA	NA	Heterosexual	Some university or more	Studying and/ or working	Good/ Excellent	Strong/ somewhat strong	No	NA	Yes	Yes	Urban/Sub	1	NA	Yes	NA	NA	NA	Yes	NA	NA	Very/ Fairly interested	Yes	NA	NA	NA	NA	89000	NA	NA	NA	No	NA	No	NA	NA	48	16	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	No	Some university or more	27	NA	23 to 24	2	0 or 1 risk factor	22-25	1997	NA	NA	Not immigrant or <=18 at arrival	18 to 24	QS1_9_GENDER1_1_1	0	0	0	0	0
5	ECR-vlt6-197730841	6-Feb-20	15:10:00	23	2	2	T2N	2	1	1	2	2	1	825	3	NA	1	NA	1	NA	NA	NA	NA	NA	NA	NA	1	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	NA	NA	en_US	CA	23	1	Alberta	1	Urban	Métis	2	You may also belong to one or more racial or cultural groups on the following list Check all that apply	2	0	0	0	1	0	0	0	0	0	0	0	0	0	0	NA	Yes	NA	NA	1	0	0	0	0	0	NA	No	Bisexual, pansexual, or queer	NA	Yes	Yes	13	1	3	0	0	0	0	1	0	0	0	0	0	0	0	0	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	4	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	Yes	12	No	NA	NA	NA	Working (paid work for at least 1 hr/week)	NA	NA	NA	NA	NA	Bi-weekly	NA	NA	NA	NA	NA	NA	1000	1	NA	NA	Yes	Yes	Unsure	NA	NA	NA	NA	2	No	Yes	1	1	NA	Yes	1	0	1	1	1	0	1	0	0	0	0	0	NA	MrL	MissM	Mom	1	1	1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	NA	Yes	3	NA	4	Outside somewhere don’t remember	4	1	0	0	1	1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	NA	No	1	NA	1	NA	4	1	1	1	1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	My mom	No	1	NA	4	At home	5	2	1	0	1	1	NA	2	More than 6 years older than me	The mentor did	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	3	2	2	3	2	4	4	3	4	4	3	3	2	1	2	3	3	3	3	2	3	2	2	3	3	3	3	3	3	2	2	2	Yes	Yes	No	No	Yes	No	No	No	No	No	No	No	No	No	NA	Sometimes true	Not very true	Not very true	Sometimes true	Sometimes true	Not very true	Not very true	Not very true	Sometimes true	1	Idk	1	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	2	4	2	3	1	1	3	2	1	Quite a bit	A little	Some	A little	Quite a bit	Quite a bit	A lot	Quite a bit	Quite a bit	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	1	2	2	1	3	3	2	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	2	1	1	1	1	1	2	2	3	2	2	2	2	2	2	1	2	2	2	3	3	3	3	2	1	1	1	3	2	3	NA	Unsure	Unsure	Unsure	Unsure	Unsure	Agree	Unsure	Unsure	NA	NA	University diploma or certificate ABOVE Bachelor’s Degree	NA	1	Neutral	Neutral	Neutral	Neutral	3	3	3	3	3	3	3	3	3	3	Fair	3	4	3	3	2	3	3	Somewhat weak	4	3	4	3	3	1	2	2	2	1	2	0	1	NA	NA	NA	NA	NA	NA	No	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	Fairly interested	Unsure	1	1	1	0	0	1	1	NA	1	1	1	0	0	1	NA	1 to 5	16	1	0	0	1	1	1	1	1	0	0	0	0	0	0	0	0	0	1	0	0	0	1	0	0	0	1	0	Indigenous	Non-white or combination	2	1 or more risk factors	5	1 or more risk factors	Woman	Yes mentor	NA	Other	NA	Studying and/ or working	Poor or fair	Weak/ somewhat weak	Yes	Yes	Yes	No	Urban/Sub	1	Yes	Yes	NA	NA	NA	No	NA	NA	Very/ Fairly interested	Yes	NA	NA	24000	NA	24000	Yes	Yes	Yes	No	Yes	No	Always positive	Positive experience	34	12	No	Yes	1	0	0	0	0	0	0	0	0	0	0	0	0	0	One-on-one	At School	12+ months	1	1	1	Yes	No	Some university or more	21	Non-youth initiated	23 to 24	2	2 or more risk ractors	22-25	1997	NA	NA	Not immigrant or <=18 at arrival	18 to 24	QS1_9_GENDER1_1_1	0	0	624000	0	624000

1.2.1 Histograms to examine distributions:

1.2.1.1 Total estimated yearly income:

ggplot(youth, aes(x = total_yearly_income)) +
    geom_histogram() +
    scale_y_log10() +
    labs(title = "Distribution of total estimated yearly income",
    x = "Estimate Total Yearly Income ($)") +
    theme_minimal()

1.2.1.2 Frequency count of each gender identity (QS1_9_gender):

ggplot(youth, aes(x = QS1_9_gender, fill = QS1_9_gender)) +
    geom_bar() +
    theme(axis.text.x = element_text(angle = 45, hjust = 1))

1.2.1.3 Compare gender identity to estimated yearly total income (total_yearly_income):

ggplot(youth, aes(x = QS1_9_gender, y = total_yearly_income, fill = QS1_9_gender)) +
    geom_bar(stat = "identity") +
    labs(x = "Gender Indentity", y = "Total estimated yearly income ($)") +
    theme(axis.text.x = element_text(angle = 45, hjust = 1))

ggplot(youth, aes(x = QS1_9_gender, y = total_yearly_income, fill = QS1_9_gender)) +
    geom_boxplot() +
    labs(x = "Gender Indentity", y = "Total estimated yearly income ($)") +
    theme(axis.text.x = element_text(angle = 45, hjust = 1))

youth |>
filter(total_yearly_income < 29380) |>
ggplot( aes(x = QS1_9_gender, y = total_yearly_income, fill = QS1_9_gender)) +
    geom_bar(stat = "identity", position = "dodge") +
    labs(x = "Gender Indentity", y = "Total estimated yearly income ($)") +
    theme(axis.text.x = element_text(angle = 45, hjust = 1))

youth |>
filter(total_yearly_income < 29380) |>
ggplot( aes(x = QS1_9_gender, y = total_yearly_income, fill = QS1_9_gender)) +
    geom_bar(stat = "identity", position = "stack") +
    labs(x = "Gender Indentity", y = "Total estimated yearly income ($)") +
    theme(axis.text.x = element_text(angle = 45, hjust = 1))

1.2.1.4 Comparing further education (QS1_21_FURTHEDUCA) and current income:

ggplot(youth, aes(x = QS1_21_FURTHEDUCA, y = total_yearly_income, fill = QS1_9_gender)) +
    geom_boxplot(outliers = FALSE) +
    theme(axis.text.x = element_text(angle = 45, hjust = 1))

1.2.1.5 Remove outlier in no group by removing the observations with total_yearly_income $29,380, the low-income for an individual person in 2024 in canada.

youth |>
filter(total_yearly_income < 29380) |>
ggplot(aes(x = QS1_21_FURTHEDUCA, y = total_yearly_income, fill = QS1_9_gender)) +
    geom_bar(stat = "identity", position = "dodge") +
    theme(axis.text.x = element_text(angle = 45, hjust = 1))

1.2.1.6 Visualize Mental health outcome QS4_9_MENTALHEALTH (or QS4_9_MENTALHEALTH_cat) / QS4_11_BELONGING depending on early mentee experience (QS2_3_PRESENCEOFM_cat or QS2_3_PRESENCEOFM)

youth |>
    filter(!is.na(QS4_9_MENTALHEALTH_cat)) |>
    drop_na(QS2_3_PRESENCEOFM_cat) |>
    ggplot(aes(x = QS2_3_PRESENCEOFM_cat, fill = QS4_9_MENTALHEALTH_cat)) +
    geom_bar(position = "dodge") +
    labs(x = "Early life mentor experience (age 6-11 years old)", fill = "Current Mental Health Rating")

youth |>
    filter(!is.na(QS4_9_MENTALHEALTH_cat)) |>
    drop_na(QS2_3_PRESENCEOFM_cat) |>
    ggplot(aes(x = QS2_3_PRESENCEOFM_cat, fill = QS4_9_MENTALHEALTH_cat)) +
    geom_bar(position = "fill") +
    labs(x = "Early life mentor experience (age 6-11 years old)", fill = "Current Mental Health Rating")

1.3 Python: Visualization

1.3.0.1 Remove unesscary columns and indicate text columns

df_dropped = youth.iloc[:, 41:]

# drop logic and validation columns
df_dropped = df_dropped.drop(columns=['QAge_Validation', 'Logic_QS1_6_Qtext', 'Logic_Qtext', 'QS1_8_Validation', 'Logic_QS1_26_Ask', 'QS1_29_Validation', 
                              'QS1_30_MValidatio', 'QS1_30_SMValidati', 'QS1_31_BWValidati', 'QS1_32_WValidatio', 'QS2_10_Validation', 'Logic_QS2_14_Ask','Logic_MENTORID1_1_1',
                              'Logic_MENTORID1_2_2', 'Logic_MENTORID1_3_3', 'Logic_AP_QS2_23', 'Logic_QS2_27_Ask', 'Logic_QS2_34_Valid', 'Logic_QS2_35_Ask', 'Logic_QS2_35_Mask1_1_1',
                              'Logic_QS2_35_Mask1_2_2', 'Logic_QS2_35_Mask1_3_3', 'Logic_QS2_35_Mask1_4_4', 'Logic_QS2_35_Mask1_5_5', 'Logic_QS2_35_Mask1_6_6', 'Logic_QS2_35_Mask1_7_7',
                              'Logic_QS2_35_Mask1_8_8', 'Logic_QS2_35_Mask1_9_9', 'Logic_QS2_35_Mask1_10_10', 'QS4_14_Validatio', 'QS4_15_Validatio', 'QS4_19_Validatio', 'QS4_23_Validatio'
    
                              ])

text_columns = ['QS1_6_Other', 'QS1_9_Other', 'QS1_11_Other', 'QS1_16_Other', 'QS1_18_Other_1', 'QS1_18_Other_2', 'QS1_18_Other_3', 'QS1_18_Other_4', 'QS1_18_Other_5', 'QS1_18_Other_6', 'QS1_18_Other_7', 'QS1_18_Other_8', 'QS1_18_Other_9', 'QS1_18_Other_10', 
                'QS1_18_Other_11', 'QS1_22_Other', 'QS1_26_Other', 'QS1_27_Other', 'QS2_13_Other', 'QS2_14_MENTORID', 'QS2_14_MENTORID_2', 'QS2_14_MENTORID_3', 'QS2_18_LOCATION_1_O', 'QS2_15_RELATIONSHIP2', 'QS2_17_TYPE_2_Other', 'QS2_18_LOCATION_2_O', 'QS2_15_RELATIONSHIP3',
                'QS2_17_TYPE_3_Other', 'QS2_18_LOCATION_3_O', 'QS2_25_YOUTHINIT2', 'QS2_27_MENTORPROGRA2', 'QS2_33_TRANSITIONS_Ot', 'QS2_34_SUPPORTS_Ot', 'QS2_38_NETGATIVEMENTO', 'QS3_2_TRANSITIONWITHOUTMEN', 'QS3_3_TRANSITIONSWITHOUTMENTO', 'QS4_4_Other', 'QS4_5_SATEDU_Other']

                

1.3.0.2 Plot a histogram of age

df_dropped['QS1_1_AGE'].plot.hist(bins=10, edgecolor='black')

<Axes: ylabel='Frequency'>

plt.xlabel('Age')

Text(0.5, 0, 'Age')

plt.ylabel('Frequency')

Text(0, 0.5, 'Frequency')

plt.title('Histogram of Age')

Text(0.5, 1.0, 'Histogram of Age')

plt.show()

1.3.0.3 Table of observations for each province/territory

province_counts = df_dropped['QS1_2_PROV'].value_counts()
print(province_counts)

QS1_2_PROV
Ontario                      1097
Quebec                        610
Alberta                       353
British Columbia              347
Manitoba                       95
Saskatchewan                   87
New Brunswick                  67
Nova Scotia                    60
Outside of Canada              37
Newfoundland and Labrador      33
Prefer not to say              21
Prince Edward Island           14
Unsure                          7
Yukon                           6
Northwest Territories           3
Nunavut                         1
Name: count, dtype: int64

1.3.0.4 Employment counts for indigenous status

youth['QS1_25_EMPLOYMENT_abrivated'] = youth['QS1_25_EMPLOYMENT'].replace({
    'Working (paid work for at least 1 hr/week)': 'Working',
    'Studying or in education/training': 'Studying',
    'Neither of the above': 'Neither',
    'Both': 'Both'
})

youth['QS1_4_INDIGENOUS_abrivated'] = youth['QS1_4_INDIGENOUS'].replace({
    "I don't identify as a member of these communities": 'Non-Indigenous',
    'First Nations (North American Indian)': 'First Nations',
    'Prefer not to say': 'Prefer not to say',
    'Unsure': 'Unsure',
    'Métis': 'Métis',
    'Inuk (Inuit)': 'Inuk'
})

table = pd.crosstab(youth['QS1_4_INDIGENOUS_abrivated'], youth['QS1_25_EMPLOYMENT_abrivated'])
print(table)

QS1_25_EMPLOYMENT_abrivated  Both  Neither  Studying  Working
QS1_4_INDIGENOUS_abrivated                                   
First Nations                  23       29        38       85
Inuk                            2        1         2        8
Métis                          14       19        14       59
Non-Indigenous                263      293       503     1254
Prefer not to say              12       36        30       33
Unsure                         20       23        29       48

1.3.0.5 Presence of mentors in early life and adolescence

presence_of_ment_611 = df_dropped['QS2_3_PRESENCEOFM'].value_counts()
presence_of_ment_1218 = df_dropped['QS2_9_PRESENCEOFA'].value_counts()

print("Presence of Mentor (ages 6-11) (QS2_3_PRESENCEOFM):")

Presence of Mentor (ages 6-11) (QS2_3_PRESENCEOFM):

print(presence_of_ment_611)

QS2_3_PRESENCEOFM
No                   1451
Yes                  1059
Unsure                275
Prefer not to say      53
Name: count, dtype: int64

print("Presence of Mentor (ages 12-18) (QS2_3_PRESENCEOFM):")

Presence of Mentor (ages 12-18) (QS2_3_PRESENCEOFM):

print(presence_of_ment_1218)

QS2_9_PRESENCEOFA
No                   1373
Yes                  1148
Unsure                264
Prefer not to say      53
Name: count, dtype: int64