public repository of the uncongeniality_analysis. Initial publication

This commit is contained in:
Orihara Izaya
2024-07-22 09:51:10 +02:00
commit f2bb63be67
159 changed files with 9611 additions and 0 deletions
@@ -0,0 +1,10 @@
---
analysis:
- !bayesian_regression
name: "Example_bayes_regression"
dataset: "data"
independent_variables:
- 'bayes-corrected (q=0.25) valence'
- 'totalvotes'
dependent_variable: 'number O(n+1)-replies'
...
@@ -0,0 +1,8 @@
---
analysis:
- !comparison_variance_in_and_between_group
name: "Example_comparison_variance_in_and_between_group"
dataset: "data"
variable: 'bayes-corrected (q=0.25) variance'
group: 'user_id'
...
@@ -0,0 +1,22 @@
---
analysis:
- !linear_regression
name: "Example_linear_regression"
dataset: "data"
independent_variables:
- 'bayes-corrected (q=0.25) valence'
- 'totalvotes'
dependent_variable: 'number O(n+1)-replies'
standardize: false
- !increase_per_up_and_downvote_from_totalvotes_and_valence
name: "Example_increase_per_up_and_downvote"
dataset: "data"
weight_as_distribution_quantile: true
weight_m: 0.25
model_name: "Example_linear_regression"
step:
- 0
- 1
startpoint: "average"
...
@@ -0,0 +1,17 @@
---
analysis:
- !linear_regression
name: "Example_linear_regression"
dataset: "data"
independent_variables:
- 'bayes-corrected (q=0.25) valence'
- 'totalvotes'
dependent_variable: 'number O(n+1)-replies'
standardize: false
report_effect_size: false
- !function_inverse_bayes_transformed_regression
name: "function_Example"
dataset: "data"
model_name: "Example_linear_regression"
...
@@ -0,0 +1,17 @@
---
analysis:
- !linear_regression_grouped
name: "Example_grouped_linear_regression"
dataset: "data"
independent_variables:
- 'bayes-corrected (q=0.25) valence'
- 'totalvotes'
dependent_variable: 'number O(n+1)-replies'
aggregation_functions:
- 'mean'
- 'sum'
- 'sum'
group_by: 'user_id'
standardize: false
print_detailed_coefficients: true
...
@@ -0,0 +1,11 @@
---
analysis:
- !linear_regression
name: "Example_linear_regression"
dataset: "data"
independent_variables:
- 'bayes-corrected (q=0.25) valence'
- 'totalvotes'
dependent_variable: 'number O(n+1)-replies'
standardize: false
...
@@ -0,0 +1,8 @@
---
analysis:
- !paired_ttest
name: "Example_paired_ttest"
dataset: "data"
variable_1: 'bayes-corrected (q=0.25) extremity'
variable_2: 'mean bayes-corrected (q=0.25) extremity of replies'
...
@@ -0,0 +1,8 @@
---
analysis:
- !pearson_correlation
name: "Example_pearson_correlation"
dataset: "data"
variable_1: 'bayes-corrected (q=0.25) extremity'
variable_2: 'mean bayes-corrected (q=0.25) extremity of replies'
...
@@ -0,0 +1,8 @@
---
analysis:
- !ttest
name: "Example_ttest"
dataset: "data"
variable_1: 'bayes-corrected (q=0.25) extremity'
variable_2: 'mean bayes-corrected (q=0.25) extremity of replies'
...
@@ -0,0 +1,11 @@
---
descriptive:
- !descriptive_aggregated
name: "Example_overview"
dataset: "data"
variables:
- 'Count'
- 'totalvotes'
aggregation_function: "sum"
group_by: "user_id"
...
@@ -0,0 +1,40 @@
---
descriptive:
- !descriptive_overview
name: "Example_overview"
dataset: "data"
group_by: "order"
metrics:
- operation: "count"
column: null
- operation: "sum"
column: "number O(n+1)-replies"
- operation: "count_nonzero"
column: "number O(n+1)-replies"
- operation: "count_nonzero"
column: "totalvotes"
- operation: "sum"
column: "totalvotes"
- operation: "sum"
column: "upvotes"
- operation: "sum"
column: "downvotes"
- operation: "count_nonzero"
column: "totalvotes"
- operation: "mean"
column: "valence"
- operation: "std_dev"
column: "valence"
- operation: "mean"
column: "bayes-corrected (q=0.25) valence"
- operation: "std_dev"
column: "bayes-corrected (q=0.25) valence"
- operation: "mean"
column: "extremity"
- operation: "std_dev"
column: "extremity"
- operation: "mean"
column: "bayes-corrected (q=0.25) extremity"
- operation: "std_dev"
column: "bayes-corrected (q=0.25) extremity"
...
@@ -0,0 +1,9 @@
---
descriptive:
- !percentage_of_dataset_under_condition
name: "Example_percentage_of_dataset_under_condition"
dataset: "data"
variable: "totalvotes"
comparison: "smaller"
condition: 10
...
@@ -0,0 +1,13 @@
---
visualization:
- !barchart
name: 'Example_barchart'
dataset: "data"
variable_x_axis: 'bayes-corrected (q=0.25) extremity'
variable_y_axis: None
x_axis_label: 'bayes-corrected (q=0.25) extremity'
y_axis_label: 'Count'
chart_orientation: 'h'
sort_order: 'ascending'
title: 'Barchart'
...
@@ -0,0 +1,11 @@
---
visualization:
- !boxplot
name: 'Example_boxplot'
dataset: "data"
variable_1: 'bayes-corrected (q=0.25) extremity'
variable_2: 'mean bayes-corrected (q=0.25) extremity of replies'
x_axis_label: ''
y_axis_label: 'Extremity value'
title: 'Box plot comparing bayes-corrected extremity with the mean extremity of replies'
...
@@ -0,0 +1,27 @@
---
analysis:
- !linear_regression
name: "Example_linear_regression"
dataset: "data"
independent_variables:
- 'bayes-corrected (q=0.25) valence'
- 'totalvotes'
dependent_variable: 'number O(n+1)-replies'
standardize: false
report_effect_size: false
- !function_inverse_bayes_transformed_regression
name: "function_Example"
dataset: "data"
model_name: "Example_linear_regression"
visualization:
- !contourplot
name: "Example_surfaceplot"
dataset: "data"
function_name: "function_Example"
x_axis_maximum: 20
y_axis_maximum: 20
x_axis_label: "downvotes"
y_axis_label: "upvotes"
...
@@ -0,0 +1,15 @@
---
visualization:
- !count_distribution
name: 'Example_count_distribution'
dataset: "data"
variable: 'user_id'
x_axis_label: 'Number of comments'
y_axis_label: 'Number of users'
x_axis_limits:
- 0
- 10
x_axis_logarithmic_scaling: false
y_axis_logarithmic_scaling: false
title: 'Distribution of Comments over Users'
...
@@ -0,0 +1,10 @@
---
visualization:
- !densityplot
name: 'Example_densityplot'
dataset: "data"
variable_x_axis: 'bayes-corrected (q=0.25) extremity'
variable_y_axis: 'mean bayes-corrected (q=0.25) extremity of replies'
data_breakpoints:
- 0
...
@@ -0,0 +1,37 @@
---
analysis:
- !linear_regression
name: "Example_linear_regression_subset_1"
dataset: "data_subset_1"
independent_variables:
- 'bayes-corrected (q=0.25) valence'
- 'totalvotes'
dependent_variable: 'number O(n+1)-replies'
standardize: true
- !linear_regression
name: "Example_linear_regression_subset_2"
dataset: "data_subset_2"
independent_variables:
- 'bayes-corrected (q=0.25) valence'
- 'totalvotes'
dependent_variable: 'number O(n+1)-replies'
standardize: true
visualization:
- !forestplot:
name: "Example_forestplot"
regression_model_names:
- "Example_linear_regression_subset_1"
- "Example_linear_regression_subset_2"
regression_model_labels:
- "Subset 1"
- "Subset 2"
coefficient_names:
- "bayes-corrected (q=0.25) valence"
- "totalvotes"
x_axis_minimum: 0
dotsize: 5
x_axis_label: "Standardized coefficient (95% Confidence Interval)"
...
@@ -0,0 +1,27 @@
---
analysis:
- !paired_ttest
name: "Example_paired_ttest_subset_1"
dataset: "data_subset_1"
variable_1: 'bayes-corrected (q=0.25) extremity'
variable_2: 'mean bayes-corrected (q=0.25) extremity of replies'
- !paired_ttest
name: "Example_paired_ttest_subset_2"
dataset: "data_subset_2"
variable_1: 'bayes-corrected (q=0.25) extremity'
variable_2: 'mean bayes-corrected (q=0.25) extremity of replies'
visualization:
- !forestplot:
name: "Example_forestplot_paired_ttest"
paired_ttest_names:
- "Example_paired_ttest_subset_1"
- "Example_paired_ttest_subset_2"
paired_ttest_labels:
- "Subset 1"
- "Subset 2"
x_axis_minimum: 0
dotsize: 5
x_axis_label: "Mean difference bayes-corrected (q=0.25) extremity (95% Confidence Interval)"
...
@@ -0,0 +1,12 @@
---
visualization:
- !grouped_histogram
name: "Example_grouped_histogram"
dataset: "data"
group_by: 'user_id'
aggregation_variable: 'bayes-corrected (q=0.25) valence'
aggregation_function: 'mean'
x_axis_label: 'Valence'
y_axis_label: 'Number of users'
title: 'Histogram of Mean Valence per User'
...
@@ -0,0 +1,17 @@
---
visualization:
- !heatmap
name: "Example_heatmap"
dataset: "data"
axis_variables:
- 'bayes-corrected (q=0.25) valence'
- 'totalvotes'
heat_variable: 'number O(n+1)-replies'
axis_maxima:
- 1
- 40
axis_minima:
- 0
- 0
logarithmic_heat_scaling: 'false'
...
@@ -0,0 +1,12 @@
---
visualization:
- !hexbinplot
name: "Example_hexbinplot"
dataset: "data"
variable_x_axis: 'bayes-corrected (q=0.25) extremity'
variable_y_axis: 'mean bayes-corrected (q=0.25) extremity of replies'
x_axis_maximum: 1
y_axis_maximum: 1
trendline: false
logarithmic_hex_scaling: false
...
@@ -0,0 +1,12 @@
---
visualization:
- !histogram
name: 'Descriptive_histogram_comments_over_totalvotes'
dataset: "data"
variable: 'totalvotes'
x_axis_label: 'Number of total votes'
y_axis_label: 'Number of comments'
x_axis_logarithmic_scaling: false
y_axis_logarithmic_scaling: true
title: ''
...
@@ -0,0 +1,14 @@
---
visualization:
- !percentage_stacked_barchart
name: 'Example_percentage_stacked_barchart'
dataset: "data"
variable_x_axis: 'section'
variables_to_compare:
- 'upvotes'
- 'downvotes'
x_axis_label: 'Section'
chart_orientation: 'h'
sort_order: 'ascending'
title: 'Stacked Barchart of Upvotes and Downvotes by Section'
...
@@ -0,0 +1,10 @@
---
visualization:
- !ridgelineplot
name: "Example_ridgelineplot"
dataset: "data"
variable_x_axis: 'bayes-corrected (q=0.25) extremity'
variable_y_axis: 'mean bayes-corrected (q=0.25) extremity of replies'
data_breakpoints:
- 0.5
...
@@ -0,0 +1,8 @@
---
visualization:
- !simple_scatterplot
name: "Example_simple_scatterplot"
dataset: "data"
variable_x_axis: 'bayes-corrected (q=0.25) extremity'
variable_y_axis: 'mean bayes-corrected (q=0.25) extremity of replies'
...
@@ -0,0 +1,14 @@
---
visualization:
- !stacked_barchart
name: 'Example_stacked_barchart'
dataset: "data"
variable_x_axis: 'section'
variable_y_axis: None
x_axis_label: 'section'
y_axis_label: 'Count'
hue: 'order'
chart_orientation: 'h'
sort_order: 'ascending'
title: 'Stacked Barchart of Comments by Section and Order'
...
@@ -0,0 +1,31 @@
---
analysis:
- !linear_regression
name: "Example_linear_regression"
dataset: "data"
independent_variables:
- 'bayes-corrected (q=0.25) valence'
- 'totalvotes'
dependent_variable: 'number O(n+1)-replies'
standardize: false
report_effect_size: false
- !function_inverse_bayes_transformed_regression
name: "function_Example"
dataset: "data"
model_name: "Example_linear_regression"
visualization:
- !surfaceplot
name: "Example_surfaceplot"
dataset: "data"
function_name: "function_Example"
x_axis_maximum: 20
y_axis_maximum: 20
x_axis_label: "downvotes"
y_axis_label: "upvotes"
z_axis_label: "replies"
elevation_angle: 45
azimuth_angle: 205
title: 'Effect of up- and downvotes according to example linear regression'
...
@@ -0,0 +1,8 @@
---
visualization:
- !violinplot
name: "Example_violinplot"
dataset: "data"
variable_x_axis: 'bayes-corrected (q=0.25) extremity'
variable_y_axis: 'mean bayes-corrected (q=0.25) extremity of replies'
...