Add an option to print figures and set font sizes.

exploration/expl_esm_adherence.py

@@ -6,7 +6,7 @@
 #       extension: .py
 #       format_name: percent
 #       format_version: '1.3'
-#       jupytext_version: 1.11.2
+#       jupytext_version: 1.11.4
 #   kernelspec:
 #     display_name: straw2analysis
 #     language: python
@@ -14,6 +14,7 @@
 # ---
 
 # %%
+# %matplotlib inline
 import os
 import sys
 

statistical_analysis/adherence.py

@@ -6,7 +6,7 @@
 #       extension: .py
 #       format_name: percent
 #       format_version: '1.3'
-#       jupytext_version: 1.11.2
+#       jupytext_version: 1.11.4
 #   kernelspec:
 #     display_name: straw2analysis
 #     language: python
@@ -14,12 +14,12 @@
 # ---
 
 # %%
+# %matplotlib inline
 import datetime
-
-# %%
 import os
 import sys
 
+import matplotlib.pyplot as plt
 import pandas as pd
 import seaborn as sns
 import statsmodels.api as sm
@@ -31,6 +31,24 @@ if nb_dir not in sys.path:
 import participants.query_db
 from features.esm import *
 
+# %%
+SAVE_FIGS = True
+FIG_HEIGHT = 5
+FIG_ASPECT = 1.6
+FIG_COLOUR = "#28827C"
+
+SMALL_SIZE = 10
+MEDIUM_SIZE = 12
+BIGGER_SIZE = 14
+
+plt.rc("font", size=SMALL_SIZE)  # controls default text sizes
+plt.rc("axes", titlesize=SMALL_SIZE)  # fontsize of the axes title
+plt.rc("axes", labelsize=MEDIUM_SIZE)  # fontsize of the x and y labels
+plt.rc("xtick", labelsize=SMALL_SIZE)  # fontsize of the tick labels
+plt.rc("ytick", labelsize=SMALL_SIZE)  # fontsize of the tick labels
+plt.rc("legend", fontsize=SMALL_SIZE)  # legend fontsize
+plt.rc("figure", titlesize=BIGGER_SIZE)  # fontsize of the figure title
+
 # %%
 baseline_si = pd.read_csv("E:/STRAWbaseline/results-survey637813.csv")
 baseline_be_1 = pd.read_csv("E:/STRAWbaseline/results-survey358134.csv")
@@ -130,7 +148,7 @@ df_adherence.describe()
 df_adherence[["gender", "startlanguage"]].value_counts()
 
 # %%
-sns.displot(df_adherence["finished_sessions"], binwidth=5, height=5)
+sns.displot(df_adherence["finished_sessions"], binwidth=5, height=FIG_HEIGHT)
 
 # %%
 lm_adherence = smf.ols(
@@ -224,12 +242,14 @@ df_session_workday = df_session_workday.assign(
 g1 = sns.displot(
     df_session_workday["time_diff_minutes"],
     binwidth=5,
-    height=5,
+    height=FIG_HEIGHT,
-    aspect=1.5,
+    aspect=FIG_ASPECT,
-    color="#28827C",
+    color=FIG_COLOUR,
 )
 g1.set_axis_labels("Time difference [min]", "Session count")
-# g1.savefig("WorkdayEMAtimeDiff.pdf")
+g1.set(xlim=(0, 570))
+if SAVE_FIGS:
+    g1.savefig("WorkdayEMAtimeDiff.pdf")
 
 # %% [markdown]
 # There are some sessions that are really close together. By design, none should be closer than 30 min. Let's take a look at those.
@@ -296,12 +316,13 @@ df_mean_daytime_interval.describe()
 g2 = sns.displot(
     df_mean_daytime_interval.time_diff_minutes,
     binwidth=5,
-    height=5,
+    height=FIG_HEIGHT,
-    aspect=1.5,
+    aspect=FIG_ASPECT,
-    color="#28827C",
+    color=FIG_COLOUR,
 )
 g2.set_axis_labels("Median time difference [min]", "Participant count")
-# g2.savefig("WorkdayEMAtimeDiffMedianParticip.pdf")
+if SAVE_FIGS:
+    g2.savefig("WorkdayEMAtimeDiffMedianParticip.pdf")
 
 # %%
 df_adherence = df_adherence.merge(
@@ -327,9 +348,9 @@ df_count_daytime_per_participant["time"].describe()
 sns.displot(
     df_count_daytime_per_participant.time,
     binwidth=1,
-    height=5,
+    height=FIG_HEIGHT,
-    aspect=1.5,
+    aspect=FIG_ASPECT,
-    color="#28827C",
+    color=FIG_COLOUR,
 )
 
 # %% [markdown]
@@ -364,13 +385,14 @@ s_evening_completed_ratio.describe()
 g3 = sns.displot(
     s_evening_completed_ratio - 0.001,
     binwidth=0.05,
-    height=5,
+    height=FIG_HEIGHT,
-    aspect=1.5,
+    aspect=FIG_ASPECT,
-    color="#28827C",
+    color=FIG_COLOUR,
 )
 g3.set_axis_labels("Ratio of days with the evening EMA filled out", "Participant count")
 g3.set(xlim=(1.01, 0.59))
-# g3.savefig("EveningEMAratioParticip.pdf")
+if SAVE_FIGS:
+    g3.savefig("EveningEMAratioParticip.pdf")
 
 # %%
 df_adherence = df_adherence.merge(
@@ -386,5 +408,3 @@ lr_ols_evening_ratio = smf.ols(
 )
 ls_result_evening_ratio = lr_ols_evening_ratio.fit()
 ls_result_evening_ratio.summary()
-
-# %%