rapids/tests/scripts/phone_feats.py

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt


path = "/rapids/data/processed/features/all_participants/all_sensor_features.csv"
df = pd.read_csv(path)

# activity_recognition

cols = [col for col in df.columns if "activity_recognition" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'activity_recognition_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_activity_recognition_values', bbox_inches='tight')
plt.close()

# applications_foreground

cols = [col for col in df.columns if "applications_foreground" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'applications_foreground_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_applications_foreground_values', bbox_inches='tight')
plt.close()

# battery

cols = [col for col in df.columns if "phone_battery" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'phone_battery_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_phone_battery_values', bbox_inches='tight')
plt.close()

# bluetooth_doryab

cols = [col for col in df.columns if "bluetooth_doryab" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'bluetooth_doryab_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_bluetooth_doryab_values', bbox_inches='tight')
plt.close()

# bluetooth_rapids

cols = [col for col in df.columns if "bluetooth_rapids" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'bluetooth_rapids_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_bluetooth_rapids_values', bbox_inches='tight')
plt.close()

# calls

cols = [col for col in df.columns if "phone_calls" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'phone_calls_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_phone_calls_values', bbox_inches='tight')
plt.close()

# data_yield

cols = [col for col in df.columns if "data_yield" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'data_yield_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_data_yield_values', bbox_inches='tight')
plt.close()

# esm

cols = [col for col in df.columns if "phone_esm" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'phone_esm_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_phone_esm_values', bbox_inches='tight')
plt.close()

# light

cols = [col for col in df.columns if "phone_light" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'phone_light_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_phone_light_values', bbox_inches='tight')
plt.close()

# locations_doryab

cols = [col for col in df.columns if "locations_doryab" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'locations_doryab_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_locations_doryab_values', bbox_inches='tight')
plt.close()

# locations_barnett

# Not working

# messages

cols = [col for col in df.columns if "phone_messages" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'phone_messages_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_phone_messages_values', bbox_inches='tight')
plt.close()

# screen

cols = [col for col in df.columns if "phone_screen" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'phone_screen_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_phone_screen_values', bbox_inches='tight')
plt.close()

# wifi_visible

cols = [col for col in df.columns if "wifi_visible" in col]
df_x = df[cols]

print(len(cols))
print(df_x)

df_x = df_x.dropna(axis=0, how="all")
sns.heatmap(df_x.isna(), xticklabels=1)
plt.savefig(f'wifi_visible_values', bbox_inches='tight')

df_q = pd.DataFrame()
for col in df_x:
    df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))

sns.heatmap(df_q, cbar=False, xticklabels=1)
plt.savefig(f'cut_wifi_visible_values', bbox_inches='tight')
plt.close()

# All features

print(len(df))
print(df)

# df = df.dropna(axis=0, how="all")
# df = df.dropna(axis=1, how="all")
sns.heatmap(df.isna())
plt.savefig(f'all_features', bbox_inches='tight')

print(df.columns[df.isna().all()].tolist())
print("All NaNs:", df.isna().sum().sum())
print("Df shape NaNs:", df.shape)