wire up Phyphox pipeline: full 561 feature extraction from raw CSV

data/norm_params.json

@@ -0,0 +1 @@
+{"tBodyAcc-mean()-X": {"min": -1.0, "max": 1.0}, "tBodyAcc-mean()-Y": {"min": -1.0, "max": 1.0}, "tBodyAcc-mean()-Z": {"min": -1.0, "max": 1.0}, "tBodyAcc-std()-X": {"min": -1.0, "max": 1.0}, "tBodyAcc-std()-Y": {"min": -0.99987292, "max": 0.91623796}, "tBodyAcc-std()-Z": {"min": -1.0, "max": 1.0}, "tBodyAcc-mad()-X": {"min": -1.0, "max": 1.0}, "tBodyAcc-mad()-Y": {"min": -1.0, "max": 0.96766404}, "tBodyAcc-mad()-Z": {"min": -1.0, "max": 1.0}, "tBodyAcc-max()-X": {"min": -1.0, "max": 1.0}, "tBodyAcc-max()-Y": {"min": -1.0, "max": 1.0}, "tBodyAcc-max()-Z": {"min": -1.0, "max": 1.0}, "tBodyAcc-min()-X": {"min": -1.0, "max": 1.0}, "tBodyAcc-min()-Y": {"min": -1.0, "max": 1.0}, "tBodyAcc-min()-Z": {"min": -1.0, "max": 1.0}, "tBodyAcc-sma()": {"min": -1.0, "max": 1.0}, "tBodyAcc-energy()-X": {"min": -1.0, "max": 1.0}, "tBodyAcc-energy()-Y": {"min": -0.9999986, "max": 1.0}, "tBodyAcc-energy()-Z": {"min": -1.0, "max": 1.0}, "tBodyAcc-iqr()-X": {"min": -1.0, "max": 1.0}, "tBodyAcc-iqr()-Y": {"min": -1.0, "max": 1.0}, "tBodyAcc-iqr()-Z": {"min": -1.0, "max": 1.0}, "tBodyAcc-entropy()-X": {"min": -1.0, "max": 0.91966171}, "tBodyAcc-entropy()-Y": {"min": -1.0, "max": 1.0}, "tBodyAcc-entropy()-Z": {"min": -1.0, "max": 1.0}, "tBodyAcc-arCoeff()-X,1": {"min": -0.92589735, "max": 1.0}, "tBodyAcc-arCoeff()-X,2": {"min": -0.9630993, "max": 0.97844881}, "tBodyAcc-arCoeff()-X,3": {"min": -1.0, "max": 1.0}, "tBodyAcc-arCoeff()-X,4": {"min": -0.82205333, "max": 1.0}, "tBodyAcc-arCoeff()-Y,1": {"min": -1.0, "max": 1.0}, "tBodyAcc-arCoeff()-Y,2": {"min": -1.0, "max": 1.0}, "tBodyAcc-arCoeff()-Y,3": {"min": -1.0, "max": 1.0}, "tBodyAcc-arCoeff()-Y,4": {"min": -1.0, "max": 1.0}, "tBodyAcc-arCoeff()-Z,1": {"min": -1.0, "max": 0.81462304}, "tBodyAcc-arCoeff()-Z,2": {"min": -0.75375375, "max": 1.0}, "tBodyAcc-arCoeff()-Z,3": {"min": -1.0, "max": 0.99720675}, "tBodyAcc-arCoeff()-Z,4": {"min": -1.0, "max": 1.0}, "tBodyAcc-correlation()-X,Y": {"min": -1.0, "max": 1.0}, "tBodyAcc-correlation()-X,Z": {"min": -1.0, "max": 1.0}, "tBodyAcc-correlation()-Y,Z": {"min": -0.97221933, "max": 1.0}, "tGravityAcc-mean()-X": {"min": -1.0, "max": 0.99154906}, "tGravityAcc-mean()-Y": {"min": -0.53522237, "max": 1.0}, "tGravityAcc-mean()-Z": {"min": -1.0, "max": 1.0}, "tGravityAcc-std()-X": {"min": -1.0, "max": 1.0}, "tGravityAcc-std()-Y": {"min": -0.99982977, "max": 1.0}, "tGravityAcc-std()-Z": {"min": -1.0, "max": 1.0}, "tGravityAcc-mad()-X": {"min": -1.0, "max": 1.0}, "tGravityAcc-mad()-Y": {"min": -0.99984878, "max": 1.0}, "tGravityAcc-mad()-Z": {"min": -1.0, "max": 1.0}, "tGravityAcc-max()-X": {"min": -1.0, "max": 1.0}, "tGravityAcc-max()-Y": {"min": -0.49387412, "max": 0.96830748}, "tGravityAcc-max()-Z": {"min": -1.0, "max": 0.99658549}, "tGravityAcc-min()-X": {"min": -1.0, "max": 1.0}, "tGravityAcc-min()-Y": {"min": -0.56815651, "max": 1.0}, "tGravityAcc-min()-Z": {"min": -1.0, "max": 1.0}, "tGravityAcc-sma()": {"min": -1.0, "max": 1.0}, "tGravityAcc-energy()-X": {"min": -1.0, "max": 0.975855}, "tGravityAcc-energy()-Y": {"min": -1.0, "max": 1.0}, "tGravityAcc-energy()-Z": {"min": -0.99999923, "max": 1.0}, "tGravityAcc-iqr()-X": {"min": -1.0, "max": 1.0}, "tGravityAcc-iqr()-Y": {"min": -0.99994572, "max": 1.0}, "tGravityAcc-iqr()-Z": {"min": -0.99996947, "max": 1.0}, "tGravityAcc-entropy()-X": {"min": -1.0, "max": 1.0}, "tGravityAcc-entropy()-Y": {"min": -1.0, "max": 1.0}, "tGravityAcc-entropy()-Z": {"min": -1.0, "max": 1.0}, "tGravityAcc-arCoeff()-X,1": {"min": -1.0, "max": 1.0}, "tGravityAcc-arCoeff()-X,2": {"min": -1.0, "max": 1.0}, "tGravityAcc-arCoeff()-X,3": {"min": -1.0, "max": 1.0}, "tGravityAcc-arCoeff()-X,4": {"min": -1.0, "max": 1.0}, "tGravityAcc-arCoeff()-Y,1": {"min": -1.0, "max": 0.81316975}, "tGravityAcc-arCoeff()-Y,2": {"min": -0.95417313, "max": 1.0}, "tGravityAcc-arCoeff()-Y,3": {"min": -1.0, "max": 1.0}, "tGravityAcc-arCoeff()-Y,4": {"min": -1.0, "max": 1.0}, "tGravityAcc-arCoeff()-Z,1": {"min": -1.0, "max": 0.64877436}, "tGravityAcc-arCoeff()-Z,2": {"min": -0.61763642, "max": 1.0}, "tGravityAcc-arCoeff()-Z,3": {"min": -1.0, "max": 0.58576939}, "tGravityAcc-arCoeff()-Z,4": {"min": -0.55400018, "max": 1.0}, "tGravityAcc-correlation()-X,Y": {"min": -1.0, "max": 1.0}, "tGravityAcc-correlation()-X,Z": {"min": -1.0, "max": 1.0}, "tGravityAcc-correlation()-Y,Z": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-mean()-X": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-mean()-Y": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-mean()-Z": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-std()-X": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-std()-Y": {"min": -1.0, "max": 0.80707793}, "tBodyAccJerk-std()-Z": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-mad()-X": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-mad()-Y": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-mad()-Z": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-max()-X": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-max()-Y": {"min": -1.0, "max": 0.62437285}, "tBodyAccJerk-max()-Z": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-min()-X": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-min()-Y": {"min": -0.74690717, "max": 1.0}, "tBodyAccJerk-min()-Z": {"min": -1.0, "max": 0.99926934}, "tBodyAccJerk-sma()": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-energy()-X": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-energy()-Y": {"min": -1.0, "max": 0.63441522}, "tBodyAccJerk-energy()-Z": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-iqr()-X": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-iqr()-Y": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-iqr()-Z": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-entropy()-X": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-entropy()-Y": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-entropy()-Z": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-arCoeff()-X,1": {"min": -0.97483758, "max": 1.0}, "tBodyAccJerk-arCoeff()-X,2": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-arCoeff()-X,3": {"min": -1.0, "max": 0.96457587}, "tBodyAccJerk-arCoeff()-X,4": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-arCoeff()-Y,1": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-arCoeff()-Y,2": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-arCoeff()-Y,3": {"min": -1.0, "max": 0.99159215}, "tBodyAccJerk-arCoeff()-Y,4": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-arCoeff()-Z,1": {"min": -1.0, "max": 0.92520697}, "tBodyAccJerk-arCoeff()-Z,2": {"min": -0.79906863, "max": 1.0}, "tBodyAccJerk-arCoeff()-Z,3": {"min": -1.0, "max": 0.93354746}, "tBodyAccJerk-arCoeff()-Z,4": {"min": -1.0, "max": 1.0}, "tBodyAccJerk-correlation()-X,Y": {"min": -1.0, "max": 0.90448}, "tBodyAccJerk-correlation()-X,Z": {"min": -1.0, "max": 0.99325846}, "tBodyAccJerk-correlation()-Y,Z": {"min": -0.95950504, "max": 1.0}, "tBodyGyro-mean()-X": {"min": -0.91404957, "max": 0.73895313}, "tBodyGyro-mean()-Y": {"min": -0.85197318, "max": 1.0}, "tBodyGyro-mean()-Z": {"min": -0.90285978, "max": 1.0}, "tBodyGyro-std()-X": {"min": -1.0, "max": 1.0}, "tBodyGyro-std()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyro-std()-Z": {"min": -1.0, "max": 1.0}, "tBodyGyro-mad()-X": {"min": -1.0, "max": 1.0}, "tBodyGyro-mad()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyro-mad()-Z": {"min": -0.99991531, "max": 1.0}, "tBodyGyro-max()-X": {"min": -1.0, "max": 1.0}, "tBodyGyro-max()-Y": {"min": -0.99801363, "max": 1.0}, "tBodyGyro-max()-Z": {"min": -0.9434386, "max": 1.0}, "tBodyGyro-min()-X": {"min": -1.0, "max": 1.0}, "tBodyGyro-min()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyro-min()-Z": {"min": -1.0, "max": 1.0}, "tBodyGyro-sma()": {"min": -1.0, "max": 1.0}, "tBodyGyro-energy()-X": {"min": -1.0, "max": 1.0}, "tBodyGyro-energy()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyro-energy()-Z": {"min": -1.0, "max": 1.0}, "tBodyGyro-iqr()-X": {"min": -1.0, "max": 1.0}, "tBodyGyro-iqr()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyro-iqr()-Z": {"min": -0.99998266, "max": 1.0}, "tBodyGyro-entropy()-X": {"min": -1.0, "max": 1.0}, "tBodyGyro-entropy()-Y": {"min": -1.0, "max": 0.972798}, "tBodyGyro-entropy()-Z": {"min": -1.0, "max": 1.0}, "tBodyGyro-arCoeff()-X,1": {"min": -1.0, "max": 1.0}, "tBodyGyro-arCoeff()-X,2": {"min": -1.0, "max": 1.0}, "tBodyGyro-arCoeff()-X,3": {"min": -1.0, "max": 1.0}, "tBodyGyro-arCoeff()-X,4": {"min": -0.96659121, "max": 0.85273955}, "tBodyGyro-arCoeff()-Y,1": {"min": -1.0, "max": 1.0}, "tBodyGyro-arCoeff()-Y,2": {"min": -1.0, "max": 1.0}, "tBodyGyro-arCoeff()-Y,3": {"min": -0.96253937, "max": 1.0}, "tBodyGyro-arCoeff()-Y,4": {"min": -1.0, "max": 1.0}, "tBodyGyro-arCoeff()-Z,1": {"min": -0.90717752, "max": 0.86609404}, "tBodyGyro-arCoeff()-Z,2": {"min": -0.92338795, "max": 0.94520707}, "tBodyGyro-arCoeff()-Z,3": {"min": -0.94730392, "max": 1.0}, "tBodyGyro-arCoeff()-Z,4": {"min": -1.0, "max": 0.98513795}, "tBodyGyro-correlation()-X,Y": {"min": -1.0, "max": 1.0}, "tBodyGyro-correlation()-X,Z": {"min": -1.0, "max": 1.0}, "tBodyGyro-correlation()-Y,Z": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-mean()-X": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-mean()-Y": {"min": -1.0, "max": 0.84803136}, "tBodyGyroJerk-mean()-Z": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-std()-X": {"min": -0.99988263, "max": 1.0}, "tBodyGyroJerk-std()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-std()-Z": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-mad()-X": {"min": -0.9998892, "max": 1.0}, "tBodyGyroJerk-mad()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-mad()-Z": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-max()-X": {"min": -1.0, "max": 0.92841647}, "tBodyGyroJerk-max()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-max()-Z": {"min": -1.0, "max": 0.97903145}, "tBodyGyroJerk-min()-X": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-min()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-min()-Z": {"min": -0.7597897, "max": 1.0}, "tBodyGyroJerk-sma()": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-energy()-X": {"min": -0.99999952, "max": 1.0}, "tBodyGyroJerk-energy()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-energy()-Z": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-iqr()-X": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-iqr()-Y": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-iqr()-Z": {"min": -0.9996578, "max": 1.0}, "tBodyGyroJerk-entropy()-X": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-entropy()-Y": {"min": -1.0, "max": 0.99093504}, "tBodyGyroJerk-entropy()-Z": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-arCoeff()-X,1": {"min": -0.90591841, "max": 1.0}, "tBodyGyroJerk-arCoeff()-X,2": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-arCoeff()-X,3": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-arCoeff()-X,4": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-arCoeff()-Y,1": {"min": -0.92113806, "max": 1.0}, "tBodyGyroJerk-arCoeff()-Y,2": {"min": -1.0, "max": 0.89744607}, "tBodyGyroJerk-arCoeff()-Y,3": {"min": -0.77359738, "max": 0.99901522}, "tBodyGyroJerk-arCoeff()-Y,4": {"min": -1.0, "max": 0.92337662}, "tBodyGyroJerk-arCoeff()-Z,1": {"min": -0.95282078, "max": 0.94558999}, "tBodyGyroJerk-arCoeff()-Z,2": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-arCoeff()-Z,3": {"min": -0.95389422, "max": 1.0}, "tBodyGyroJerk-arCoeff()-Z,4": {"min": -0.95448559, "max": 1.0}, "tBodyGyroJerk-correlation()-X,Y": {"min": -0.8952687, "max": 1.0}, "tBodyGyroJerk-correlation()-X,Z": {"min": -1.0, "max": 1.0}, "tBodyGyroJerk-correlation()-Y,Z": {"min": -1.0, "max": 0.99680328}, "tBodyAccMag-mean()": {"min": -1.0, "max": 1.0}, "tBodyAccMag-std()": {"min": -1.0, "max": 1.0}, "tBodyAccMag-mad()": {"min": -1.0, "max": 1.0}, "tBodyAccMag-max()": {"min": -1.0, "max": 1.0}, "tBodyAccMag-min()": {"min": -1.0, "max": 1.0}, "tBodyAccMag-sma()": {"min": -1.0, "max": 1.0}, "tBodyAccMag-energy()": {"min": -1.0, "max": 1.0}, "tBodyAccMag-iqr()": {"min": -1.0, "max": 1.0}, "tBodyAccMag-entropy()": {"min": -0.99537696, "max": 1.0}, "tBodyAccMag-arCoeff()1": {"min": -1.0, "max": 1.0}, "tBodyAccMag-arCoeff()2": {"min": -1.0, "max": 1.0}, "tBodyAccMag-arCoeff()3": {"min": -1.0, "max": 0.994731}, "tBodyAccMag-arCoeff()4": {"min": -1.0, "max": 1.0}, "tGravityAccMag-mean()": {"min": -1.0, "max": 1.0}, "tGravityAccMag-std()": {"min": -1.0, "max": 1.0}, "tGravityAccMag-mad()": {"min": -1.0, "max": 1.0}, "tGravityAccMag-max()": {"min": -1.0, "max": 1.0}, "tGravityAccMag-min()": {"min": -1.0, "max": 1.0}, "tGravityAccMag-sma()": {"min": -1.0, "max": 1.0}, "tGravityAccMag-energy()": {"min": -1.0, "max": 1.0}, "tGravityAccMag-iqr()": {"min": -1.0, "max": 1.0}, "tGravityAccMag-entropy()": {"min": -0.99537696, "max": 1.0}, "tGravityAccMag-arCoeff()1": {"min": -1.0, "max": 1.0}, "tGravityAccMag-arCoeff()2": {"min": -1.0, "max": 1.0}, "tGravityAccMag-arCoeff()3": {"min": -1.0, "max": 0.994731}, "tGravityAccMag-arCoeff()4": {"min": -1.0, "max": 1.0}, "tBodyAccJerkMag-mean()": {"min": -1.0, "max": 1.0}, "tBodyAccJerkMag-std()": {"min": -1.0, "max": 1.0}, "tBodyAccJerkMag-mad()": {"min": -1.0, "max": 1.0}, "tBodyAccJerkMag-max()": {"min": -1.0, "max": 0.98365438}, "tBodyAccJerkMag-min()": {"min": -1.0, "max": 1.0}, "tBodyAccJerkMag-sma()": {"min": -1.0, "max": 1.0}, "tBodyAccJerkMag-energy()": {"min": -1.0, "max": 1.0}, "tBodyAccJerkMag-iqr()": {"min": -1.0, "max": 1.0}, "tBodyAccJerkMag-entropy()": {"min": -1.0, "max": 1.0}, "tBodyAccJerkMag-arCoeff()1": {"min": -1.0, "max": 0.86283136}, "tBodyAccJerkMag-arCoeff()2": {"min": -1.0, "max": 1.0}, "tBodyAccJerkMag-arCoeff()3": {"min": -0.83055874, "max": 0.91434541}, "tBodyAccJerkMag-arCoeff()4": {"min": -1.0, "max": 0.97433286}, "tBodyGyroMag-mean()": {"min": -1.0, "max": 1.0}, "tBodyGyroMag-std()": {"min": -1.0, "max": 1.0}, "tBodyGyroMag-mad()": {"min": -1.0, "max": 1.0}, "tBodyGyroMag-max()": {"min": -1.0, "max": 1.0}, "tBodyGyroMag-min()": {"min": -0.99983528, "max": 1.0}, "tBodyGyroMag-sma()": {"min": -1.0, "max": 1.0}, "tBodyGyroMag-energy()": {"min": -1.0, "max": 1.0}, "tBodyGyroMag-iqr()": {"min": -1.0, "max": 0.96899245}, "tBodyGyroMag-entropy()": {"min": -1.0, "max": 0.99263589}, "tBodyGyroMag-arCoeff()1": {"min": -1.0, "max": 0.99352363}, "tBodyGyroMag-arCoeff()2": {"min": -1.0, "max": 1.0}, "tBodyGyroMag-arCoeff()3": {"min": -0.89991431, "max": 0.99462757}, "tBodyGyroMag-arCoeff()4": {"min": -0.99742291, "max": 1.0}, "tBodyGyroJerkMag-mean()": {"min": -1.0, "max": 1.0}, "tBodyGyroJerkMag-std()": {"min": -1.0, "max": 1.0}, "tBodyGyroJerkMag-mad()": {"min": -1.0, "max": 1.0}, "tBodyGyroJerkMag-max()": {"min": -1.0, "max": 1.0}, "tBodyGyroJerkMag-min()": {"min": -1.0, "max": 1.0}, "tBodyGyroJerkMag-sma()": {"min": -1.0, "max": 1.0}, "tBodyGyroJerkMag-energy()": {"min": -1.0, "max": 1.0}, "tBodyGyroJerkMag-iqr()": {"min": -1.0, "max": 1.0}, "tBodyGyroJerkMag-entropy()": {"min": -1.0, "max": 1.0}, "tBodyGyroJerkMag-arCoeff()1": {"min": -1.0, "max": 0.99282314}, "tBodyGyroJerkMag-arCoeff()2": {"min": -0.99766425, "max": 1.0}, "tBodyGyroJerkMag-arCoeff()3": {"min": -1.0, "max": 0.88033546}, "tBodyGyroJerkMag-arCoeff()4": {"min": -1.0, "max": 0.83672766}, "fBodyAcc-mean()-X": {"min": -1.0, "max": 1.0}, "fBodyAcc-mean()-Y": {"min": -1.0, "max": 0.97184989}, "fBodyAcc-mean()-Z": {"min": -1.0, "max": 1.0}, "fBodyAcc-std()-X": {"min": -1.0, "max": 1.0}, "fBodyAcc-std()-Y": {"min": -0.9998571, "max": 0.86033908}, "fBodyAcc-std()-Z": {"min": -1.0, "max": 1.0}, "fBodyAcc-mad()-X": {"min": -1.0, "max": 1.0}, "fBodyAcc-mad()-Y": {"min": -0.99997862, "max": 0.96120357}, "fBodyAcc-mad()-Z": {"min": -1.0, "max": 1.0}, "fBodyAcc-max()-X": {"min": -1.0, "max": 1.0}, "fBodyAcc-max()-Y": {"min": -1.0, "max": 1.0}, "fBodyAcc-max()-Z": {"min": -0.99980523, "max": 1.0}, "fBodyAcc-min()-X": {"min": -0.99999831, "max": 1.0}, "fBodyAcc-min()-Y": {"min": -1.0, "max": 1.0}, "fBodyAcc-min()-Z": {"min": -1.0, "max": 1.0}, "fBodyAcc-sma()": {"min": -1.0, "max": 1.0}, "fBodyAcc-energy()-X": {"min": -1.0, "max": 1.0}, "fBodyAcc-energy()-Y": {"min": -0.99999872, "max": 0.83686006}, "fBodyAcc-energy()-Z": {"min": -1.0, "max": 1.0}, "fBodyAcc-iqr()-X": {"min": -1.0, "max": 1.0}, "fBodyAcc-iqr()-Y": {"min": -1.0, "max": 1.0}, "fBodyAcc-iqr()-Z": {"min": -1.0, "max": 1.0}, "fBodyAcc-entropy()-X": {"min": -1.0, "max": 1.0}, "fBodyAcc-entropy()-Y": {"min": -1.0, "max": 0.90901463}, "fBodyAcc-entropy()-Z": {"min": -1.0, "max": 1.0}, "fBodyAcc-maxInds-X": {"min": -1.0, "max": 1.0}, "fBodyAcc-maxInds-Y": {"min": -1.0, "max": 1.0}, "fBodyAcc-maxInds-Z": {"min": -1.0, "max": 0.92307692}, "fBodyAcc-meanFreq()-X": {"min": -1.0, "max": 0.9141467}, "fBodyAcc-meanFreq()-Y": {"min": -1.0, "max": 1.0}, "fBodyAcc-meanFreq()-Z": {"min": -1.0, "max": 1.0}, "fBodyAcc-skewness()-X": {"min": -0.93120793, "max": 1.0}, "fBodyAcc-kurtosis()-X": {"min": -0.99941209, "max": 1.0}, "fBodyAcc-skewness()-Y": {"min": -1.0, "max": 0.97555005}, "fBodyAcc-kurtosis()-Y": {"min": -1.0, "max": 0.96627476}, "fBodyAcc-skewness()-Z": {"min": -1.0, "max": 0.9849423}, "fBodyAcc-kurtosis()-Z": {"min": -1.0, "max": 0.97998881}, "fBodyAcc-bandsEnergy()-1,8": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-9,16": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-17,24": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-25,32": {"min": -0.99999405, "max": 0.88145236}, "fBodyAcc-bandsEnergy()-33,40": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-41,48": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-49,56": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-57,64": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-1,16": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-17,32": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-33,48": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-49,64": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-1,24": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-25,48": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-1,8.1": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-9,16.1": {"min": -1.0, "max": 0.94996979}, "fBodyAcc-bandsEnergy()-17,24.1": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-25,32.1": {"min": -1.0, "max": 0.95807252}, "fBodyAcc-bandsEnergy()-33,40.1": {"min": -1.0, "max": 0.84661001}, "fBodyAcc-bandsEnergy()-41,48.1": {"min": -1.0, "max": 0.89774723}, "fBodyAcc-bandsEnergy()-49,56.1": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-57,64.1": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-1,16.1": {"min": -1.0, "max": 0.86657061}, "fBodyAcc-bandsEnergy()-17,32.1": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-33,48.1": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-49,64.1": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-1,24.1": {"min": -0.99999419, "max": 0.8210904}, "fBodyAcc-bandsEnergy()-25,48.1": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-1,8.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-9,16.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-17,24.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-25,32.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-33,40.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-41,48.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-49,56.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-57,64.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-1,16.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-17,32.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-33,48.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-49,64.2": {"min": -0.99999706, "max": 1.0}, "fBodyAcc-bandsEnergy()-1,24.2": {"min": -1.0, "max": 1.0}, "fBodyAcc-bandsEnergy()-25,48.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-mean()-X": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-mean()-Y": {"min": -1.0, "max": 0.64680948}, "fBodyAccJerk-mean()-Z": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-std()-X": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-std()-Y": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-std()-Z": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-mad()-X": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-mad()-Y": {"min": -1.0, "max": 0.80506356}, "fBodyAccJerk-mad()-Z": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-max()-X": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-max()-Y": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-max()-Z": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-min()-X": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-min()-Y": {"min": -0.99999774, "max": 1.0}, "fBodyAccJerk-min()-Z": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-sma()": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-energy()-X": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-energy()-Y": {"min": -1.0, "max": 0.63432019}, "fBodyAccJerk-energy()-Z": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-iqr()-X": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-iqr()-Y": {"min": -1.0, "max": 0.64132146}, "fBodyAccJerk-iqr()-Z": {"min": -0.9991623, "max": 1.0}, "fBodyAccJerk-entropy()-X": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-entropy()-Y": {"min": -1.0, "max": 0.99682502}, "fBodyAccJerk-entropy()-Z": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-maxInds-X": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-maxInds-Y": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-maxInds-Z": {"min": -1.0, "max": 0.96}, "fBodyAccJerk-meanFreq()-X": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-meanFreq()-Y": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-meanFreq()-Z": {"min": -1.0, "max": 0.67862794}, "fBodyAccJerk-skewness()-X": {"min": -1.0, "max": 0.82920557}, "fBodyAccJerk-kurtosis()-X": {"min": -1.0, "max": 0.66004197}, "fBodyAccJerk-skewness()-Y": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-kurtosis()-Y": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-skewness()-Z": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-kurtosis()-Z": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-1,8": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-9,16": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-17,24": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-25,32": {"min": -0.99999606, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-33,40": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-41,48": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-49,56": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-57,64": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-1,16": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-17,32": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-33,48": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-49,64": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-1,24": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-25,48": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-1,8.1": {"min": -1.0, "max": 0.70292796}, "fBodyAccJerk-bandsEnergy()-9,16.1": {"min": -1.0, "max": 0.89173636}, "fBodyAccJerk-bandsEnergy()-17,24.1": {"min": -1.0, "max": 0.90836103}, "fBodyAccJerk-bandsEnergy()-25,32.1": {"min": -1.0, "max": 0.88786954}, "fBodyAccJerk-bandsEnergy()-33,40.1": {"min": -1.0, "max": 0.63241538}, "fBodyAccJerk-bandsEnergy()-41,48.1": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-49,56.1": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-57,64.1": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-1,16.1": {"min": -1.0, "max": 0.89789843}, "fBodyAccJerk-bandsEnergy()-17,32.1": {"min": -1.0, "max": 0.9303172}, "fBodyAccJerk-bandsEnergy()-33,48.1": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-49,64.1": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-1,24.1": {"min": -1.0, "max": 0.91489223}, "fBodyAccJerk-bandsEnergy()-25,48.1": {"min": -1.0, "max": 0.80737469}, "fBodyAccJerk-bandsEnergy()-1,8.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-9,16.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-17,24.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-25,32.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-33,40.2": {"min": -0.99998949, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-41,48.2": {"min": -0.99999894, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-49,56.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-57,64.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-1,16.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-17,32.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-33,48.2": {"min": -0.99996684, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-49,64.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-1,24.2": {"min": -1.0, "max": 1.0}, "fBodyAccJerk-bandsEnergy()-25,48.2": {"min": -0.99999585, "max": 1.0}, "fBodyGyro-mean()-X": {"min": -1.0, "max": 1.0}, "fBodyGyro-mean()-Y": {"min": -1.0, "max": 1.0}, "fBodyGyro-mean()-Z": {"min": -1.0, "max": 1.0}, "fBodyGyro-std()-X": {"min": -1.0, "max": 1.0}, "fBodyGyro-std()-Y": {"min": -1.0, "max": 1.0}, "fBodyGyro-std()-Z": {"min": -1.0, "max": 1.0}, "fBodyGyro-mad()-X": {"min": -1.0, "max": 1.0}, "fBodyGyro-mad()-Y": {"min": -1.0, "max": 1.0}, "fBodyGyro-mad()-Z": {"min": -1.0, "max": 1.0}, "fBodyGyro-max()-X": {"min": -1.0, "max": 1.0}, "fBodyGyro-max()-Y": {"min": -1.0, "max": 1.0}, "fBodyGyro-max()-Z": {"min": -1.0, "max": 1.0}, "fBodyGyro-min()-X": {"min": -0.99999996, "max": 0.46519723}, "fBodyGyro-min()-Y": {"min": -0.9999967, "max": 0.79449806}, "fBodyGyro-min()-Z": {"min": -0.99999972, "max": 1.0}, "fBodyGyro-sma()": {"min": -1.0, "max": 1.0}, "fBodyGyro-energy()-X": {"min": -1.0, "max": 1.0}, "fBodyGyro-energy()-Y": {"min": -1.0, "max": 1.0}, "fBodyGyro-energy()-Z": {"min": -1.0, "max": 1.0}, "fBodyGyro-iqr()-X": {"min": -1.0, "max": 1.0}, "fBodyGyro-iqr()-Y": {"min": -1.0, "max": 1.0}, "fBodyGyro-iqr()-Z": {"min": -1.0, "max": 1.0}, "fBodyGyro-entropy()-X": {"min": -1.0, "max": 1.0}, "fBodyGyro-entropy()-Y": {"min": -1.0, "max": 1.0}, "fBodyGyro-entropy()-Z": {"min": -1.0, "max": 1.0}, "fBodyGyro-maxInds-X": {"min": -1.0, "max": 1.0}, "fBodyGyro-maxInds-Y": {"min": -1.0, "max": 0.80645161}, "fBodyGyro-maxInds-Z": {"min": -1.0, "max": 0.65517241}, "fBodyGyro-meanFreq()-X": {"min": -1.0, "max": 1.0}, "fBodyGyro-meanFreq()-Y": {"min": -1.0, "max": 0.99374103}, "fBodyGyro-meanFreq()-Z": {"min": -0.96634502, "max": 1.0}, "fBodyGyro-skewness()-X": {"min": -1.0, "max": 0.92089008}, "fBodyGyro-kurtosis()-X": {"min": -1.0, "max": 0.8944949}, "fBodyGyro-skewness()-Y": {"min": -1.0, "max": 0.98132937}, "fBodyGyro-kurtosis()-Y": {"min": -0.99821279, "max": 0.97760819}, "fBodyGyro-skewness()-Z": {"min": -0.90898061, "max": 0.9035711}, "fBodyGyro-kurtosis()-Z": {"min": -1.0, "max": 0.857113}, "fBodyGyro-bandsEnergy()-1,8": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-9,16": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-17,24": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-25,32": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-33,40": {"min": -0.99999991, "max": 1.0}, "fBodyGyro-bandsEnergy()-41,48": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-49,56": {"min": -0.99999967, "max": 1.0}, "fBodyGyro-bandsEnergy()-57,64": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-1,16": {"min": -0.99999982, "max": 1.0}, "fBodyGyro-bandsEnergy()-17,32": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-33,48": {"min": -0.99999696, "max": 1.0}, "fBodyGyro-bandsEnergy()-49,64": {"min": -0.99999982, "max": 1.0}, "fBodyGyro-bandsEnergy()-1,24": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-25,48": {"min": -0.99999832, "max": 1.0}, "fBodyGyro-bandsEnergy()-1,8.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-9,16.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-17,24.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-25,32.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-33,40.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-41,48.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-49,56.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-57,64.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-1,16.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-17,32.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-33,48.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-49,64.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-1,24.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-25,48.1": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-1,8.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-9,16.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-17,24.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-25,32.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-33,40.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-41,48.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-49,56.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-57,64.2": {"min": -0.99999999, "max": 1.0}, "fBodyGyro-bandsEnergy()-1,16.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-17,32.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-33,48.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-49,64.2": {"min": -1.0, "max": 1.0}, "fBodyGyro-bandsEnergy()-1,24.2": {"min": -0.99999974, "max": 1.0}, "fBodyGyro-bandsEnergy()-25,48.2": {"min": -1.0, "max": 1.0}, "fBodyAccMag-mean()": {"min": -0.99989278, "max": 1.0}, "fBodyAccMag-std()": {"min": -1.0, "max": 1.0}, "fBodyAccMag-mad()": {"min": -1.0, "max": 1.0}, "fBodyAccMag-max()": {"min": -1.0, "max": 1.0}, "fBodyAccMag-min()": {"min": -1.0, "max": 1.0}, "fBodyAccMag-sma()": {"min": -0.99989278, "max": 1.0}, "fBodyAccMag-energy()": {"min": -1.0, "max": 1.0}, "fBodyAccMag-iqr()": {"min": -1.0, "max": 1.0}, "fBodyAccMag-entropy()": {"min": -1.0, "max": 1.0}, "fBodyAccMag-maxInds": {"min": -1.0, "max": 1.0}, "fBodyAccMag-meanFreq()": {"min": -1.0, "max": 1.0}, "fBodyAccMag-skewness()": {"min": -1.0, "max": 1.0}, "fBodyAccMag-kurtosis()": {"min": -1.0, "max": 1.0}, "fBodyBodyAccJerkMag-mean()": {"min": -1.0, "max": 1.0}, "fBodyBodyAccJerkMag-std()": {"min": -0.99996007, "max": 1.0}, "fBodyBodyAccJerkMag-mad()": {"min": -0.9991519, "max": 1.0}, "fBodyBodyAccJerkMag-max()": {"min": -1.0, "max": 1.0}, "fBodyBodyAccJerkMag-min()": {"min": -1.0, "max": 1.0}, "fBodyBodyAccJerkMag-sma()": {"min": -1.0, "max": 1.0}, "fBodyBodyAccJerkMag-energy()": {"min": -1.0, "max": 1.0}, "fBodyBodyAccJerkMag-iqr()": {"min": -0.99949935, "max": 1.0}, "fBodyBodyAccJerkMag-entropy()": {"min": -1.0, "max": 1.0}, "fBodyBodyAccJerkMag-maxInds": {"min": -1.0, "max": 1.0}, "fBodyBodyAccJerkMag-meanFreq()": {"min": -1.0, "max": 0.97582069}, "fBodyBodyAccJerkMag-skewness()": {"min": -1.0, "max": 1.0}, "fBodyBodyAccJerkMag-kurtosis()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroMag-mean()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroMag-std()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroMag-mad()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroMag-max()": {"min": -1.0, "max": 0.84211941}, "fBodyBodyGyroMag-min()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroMag-sma()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroMag-energy()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroMag-iqr()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroMag-entropy()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroMag-maxInds": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroMag-meanFreq()": {"min": -0.99750026, "max": 1.0}, "fBodyBodyGyroMag-skewness()": {"min": -1.0, "max": 0.96931086}, "fBodyBodyGyroMag-kurtosis()": {"min": -1.0, "max": 0.94935049}, "fBodyBodyGyroJerkMag-mean()": {"min": -0.99999636, "max": 1.0}, "fBodyBodyGyroJerkMag-std()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroJerkMag-mad()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroJerkMag-max()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroJerkMag-min()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroJerkMag-sma()": {"min": -0.99999636, "max": 1.0}, "fBodyBodyGyroJerkMag-energy()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroJerkMag-iqr()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroJerkMag-entropy()": {"min": -1.0, "max": 1.0}, "fBodyBodyGyroJerkMag-maxInds": {"min": -1.0, "max": 0.96825397}, "fBodyBodyGyroJerkMag-meanFreq()": {"min": -1.0, "max": 0.94669994}, "fBodyBodyGyroJerkMag-skewness()": {"min": -0.99535747, "max": 0.98953847}, "fBodyBodyGyroJerkMag-kurtosis()": {"min": -0.99976469, "max": 0.95684539}, "angle(tBodyAccMean,gravity)": {"min": -0.97658002, "max": 1.0}, "angle(tBodyAccJerkMean),gravityMean)": {"min": -1.0, "max": 1.0}, "angle(tBodyGyroMean,gravityMean)": {"min": -1.0, "max": 0.99870219}, "angle(tBodyGyroJerkMean,gravityMean)": {"min": -1.0, "max": 0.99607819}, "angle(X,gravityMean)": {"min": -1.0, "max": 1.0}, "angle(Y,gravityMean)": {"min": -1.0, "max": 0.47815733}, "angle(Z,gravityMean)": {"min": -1.0, "max": 1.0}}

src/phyphox_app_block.py

@@ -0,0 +1,190 @@
+"""Streamlit UI block for Tab 2 — Phyphox live sensor upload.
+
+Call from streamlit_app.py:
+
+    from phyphox_app_block import render_phyphox_tab
+    with tab2:
+        render_phyphox_tab(ffn_model, ffn_status, cnn_model, cnn_status)
+"""
+
+import json
+import os
+
+import numpy as np
+import pandas as pd
+import streamlit as st
+
+from phyphox_pipeline import process_phyphox_files, FS, WINDOW, STEP
+
+# ── Constants ─────────────────────────────────────────────────────────────────
+
+LABEL_MAP = {
+    0: "WALKING",
+    1: "WALKING_UPSTAIRS",
+    2: "WALKING_DOWNSTAIRS",
+    3: "SITTING",
+    4: "STANDING",
+    5: "LAYING",
+}
+
+EXPLANATIONS = {
+    "LAYING": "Minimal movement detected across all axes — consistent with a stationary horizontal posture.",
+    "SITTING": "Low dynamic acceleration with stable gravity — stationary upright posture.",
+    "STANDING": "Similar to sitting with slight postural micro-movements.",
+    "WALKING": "Rhythmic periodic acceleration on the vertical axis — level walking at normal cadence.",
+    "WALKING_DOWNSTAIRS": "Downward gravitational shift with higher impact peaks — descending stairs.",
+    "WALKING_UPSTAIRS": "Elevated vertical acceleration effort — climbing stairs.",
+}
+
+# ── Normalisation ─────────────────────────────────────────────────────────────
+
+@st.cache_resource
+def _load_norm_params(norm_path: str):
+    """Load per-feature min/max from norm_params.json in features.txt order."""
+    with open(norm_path) as f:
+        d = json.load(f)
+    min_vals = np.array([v["min"] for v in d.values()], dtype=np.float32)
+    max_vals = np.array([v["max"] for v in d.values()], dtype=np.float32)
+    return min_vals, max_vals
+
+
+def _normalize(features: np.ndarray, min_vals: np.ndarray, max_vals: np.ndarray) -> np.ndarray:
+    """Best-effort feature-level min-max scaling to [-1, 1].
+
+    Uses per-feature min/max observed in the UCI HAR training set. This is
+    an approximation — the UCI pipeline normalises raw signals before feature
+    extraction, so physical-unit features may fall outside the training range.
+    Values are clipped before scaling to keep outputs bounded.
+    """
+    rng = max_vals - min_vals
+    rng = np.where(rng < 1e-8, 1.0, rng)          # avoid div-by-zero
+    clipped = np.clip(features, min_vals, max_vals)
+    return 2.0 * (clipped - min_vals) / rng - 1.0
+
+
+# ── Public render function ────────────────────────────────────────────────────
+
+def render_phyphox_tab(
+    ffn_model, ffn_status: str,
+    cnn_model, cnn_status: str,
+    norm_params_path: str,
+) -> None:
+    st.subheader("Upload Phyphox sensor recording")
+    st.markdown("""
+**How to record your own data:**
+1. Install [Phyphox](https://phyphox.org/) on your phone
+2. Open **Acceleration (without g)** and **Gyroscope** — record simultaneously
+3. Hold the phone at your waist (same position as the UCI dataset)
+4. Record at least 3 seconds of a single activity
+5. Export both experiments as CSV and upload below
+    """)
+
+    col1, col2 = st.columns(2)
+    with col1:
+        acc_file = st.file_uploader(
+            "Accelerometer CSV",
+            type=["csv"],
+            key="acc_upload",
+            help="Columns: Time (s), X (m/s²), Y (m/s²), Z (m/s²)",
+        )
+    with col2:
+        gyro_file = st.file_uploader(
+            "Gyroscope CSV",
+            type=["csv"],
+            key="gyro_upload",
+            help="Columns: Time (s), X (rad/s), Y (rad/s), Z (rad/s)",
+        )
+
+    if acc_file is None or gyro_file is None:
+        st.info("Upload both files to continue.")
+        return
+
+    # ── Feature extraction ────────────────────────────────────────────────────
+    try:
+        with st.spinner("Extracting 561 features from sensor data…"):
+            features, pipeline_warnings = process_phyphox_files(acc_file, gyro_file)
+    except ValueError as err:
+        st.error(str(err))
+        return
+    except Exception as err:
+        st.error(f"Unexpected error during feature extraction: {err}")
+        return
+
+    for w in pipeline_warnings:
+        st.warning(w)
+
+    n_windows = len(features)
+    duration_s = (n_windows - 1) * (STEP / FS) + (WINDOW / FS)
+
+    c1, c2, c3 = st.columns(3)
+    c1.metric("Windows extracted", n_windows)
+    c2.metric("Approx. duration", f"{duration_s:.1f} s")
+    c3.metric("Features per window", 561)
+    st.caption(
+        f"Each window = {WINDOW / FS:.2f} s at {FS} Hz · "
+        f"50% overlap ({STEP / FS:.2f} s hop)"
+    )
+
+    # ── Normalisation ─────────────────────────────────────────────────────────
+    if os.path.exists(norm_params_path):
+        min_vals, max_vals = _load_norm_params(norm_params_path)
+        features = _normalize(features, min_vals, max_vals)
+        st.caption(
+            "Features scaled to [−1, 1] using per-feature min/max from the UCI HAR "
+            "training set. Values outside the training range are clipped before scaling."
+        )
+    else:
+        st.warning(
+            "norm_params.json not found — features are in physical units. "
+            "Predictions will be unreliable until normalisation is applied."
+        )
+
+    # ── Predictions ───────────────────────────────────────────────────────────
+    if ffn_status != "ready" and cnn_status != "ready":
+        st.warning("Models not loaded — cannot predict yet.")
+        return
+
+    st.markdown("---")
+    st.subheader("Model comparison")
+
+    left, right = st.columns(2)
+
+    def _render_model_col(col, model, status, name):
+        with col:
+            st.markdown(f"#### {name}")
+            if status != "ready":
+                st.error(f"Model not loaded — {status}")
+                return
+
+            probs_all = model.predict(features, verbose=0)       # (n_windows, 6)
+            pred_labels = [LABEL_MAP[int(np.argmax(p))] for p in probs_all]
+
+            from collections import Counter
+            vote = Counter(pred_labels).most_common(1)[0][0]
+            avg_conf = float(np.mean(np.max(probs_all, axis=1))) * 100
+
+            st.success(f"**{vote}** · {avg_conf:.1f}% avg confidence")
+            st.markdown(f"_{EXPLANATIONS[vote]}_")
+
+            if n_windows > 1:
+                with st.expander(f"Per-window breakdown ({n_windows} windows)"):
+                    rows = []
+                    for i, (p, label) in enumerate(zip(probs_all, pred_labels)):
+                        t_start = i * STEP / FS
+                        rows.append({
+                            "Window": i + 1,
+                            "Time (s)": f"{t_start:.1f}–{t_start + WINDOW/FS:.1f}",
+                            "Prediction": label,
+                            "Confidence": f"{float(np.max(p))*100:.1f}%",
+                        })
+                    st.dataframe(pd.DataFrame(rows), use_container_width=True)
+
+            mean_probs = probs_all.mean(axis=0)
+            st.markdown("**Average confidence across all classes**")
+            st.bar_chart(pd.DataFrame(
+                {"Confidence (%)": [float(mean_probs[i]) * 100 for i in range(6)]},
+                index=[LABEL_MAP[i] for i in range(6)],
+            ))
+
+    _render_model_col(left,  ffn_model, ffn_status, "Feedforward Network")
+    _render_model_col(right, cnn_model, cnn_status, "1D Convolutional Network")

src/phyphox_pipeline.py

@@ -0,0 +1,516 @@
+"""Phyphox sensor pipeline for Human Activity Recognition.
+
+Converts raw Phyphox accelerometer + gyroscope CSV exports into the
+561-feature vector expected by the UCI HAR classifier.
+
+Feature order matches features.txt exactly:
+  1-200   : time-domain 3-axis signals  (5 signals × 40 features)
+  201-265 : time-domain magnitudes      (5 signals × 13 features)
+  266-502 : frequency-domain 3-axis     (3 signals × 79 features)
+  503-554 : frequency-domain magnitudes (4 signals × 13 features)
+  555-561 : angle features              (7 features)
+"""
+
+import io
+import numpy as np
+import pandas as pd
+from scipy import signal as sp_signal
+from scipy.stats import skew, kurtosis as sp_kurtosis
+
+# ── Constants ─────────────────────────────────────────────────────────────────
+
+FS = 50        # target sampling rate Hz
+WINDOW = 128   # samples per window (2.56 s)
+STEP = 64      # hop size — 50% overlap
+AR_ORDER = 4   # Burg AR model order
+
+# 14 frequency band pairs (1-indexed, inclusive) applied per axis
+BANDS = [
+    (1, 8), (9, 16), (17, 24), (25, 32), (33, 40), (41, 48),
+    (49, 56), (57, 64), (1, 16), (17, 32), (33, 48), (49, 64),
+    (1, 24), (25, 48),
+]
+
+ACC_COLS = ["Time (s)", "X (m/s^2)", "Y (m/s^2)", "Z (m/s^2)"]
+GYRO_COLS = ["Time (s)", "X (rad/s)", "Y (rad/s)", "Z (rad/s)"]
+
+
+# ── CSV helpers ───────────────────────────────────────────────────────────────
+
+def _parse_csv(file_obj, expected_cols: list) -> pd.DataFrame:
+    """Parse a Phyphox CSV export and validate required columns.
+
+    Args:
+        file_obj: file-like object (bytes or str) from Phyphox export
+        expected_cols: list of required column names
+
+    Returns:
+        DataFrame with numeric data, NaN rows dropped
+
+    Raises:
+        ValueError: if columns are missing or file cannot be parsed
+    """
+    try:
+        raw = file_obj.read()
+        if isinstance(raw, bytes):
+            raw = raw.decode("utf-8")
+        df = pd.read_csv(io.StringIO(raw), float_precision="high")
+    except Exception as exc:
+        raise ValueError(f"Cannot parse CSV: {exc}") from exc
+
+    df.columns = [c.strip('"').strip() for c in df.columns]
+    missing = [c for c in expected_cols if c not in df.columns]
+    if missing:
+        raise ValueError(
+            f"Missing columns {missing}. Found: {list(df.columns)}. "
+            "Check you uploaded the correct Phyphox CSV (Accelerometer or Gyroscope)."
+        )
+    return df[expected_cols].apply(pd.to_numeric, errors="coerce").dropna()
+
+
+# ── DSP helpers ───────────────────────────────────────────────────────────────
+
+def _butter_lp(data: np.ndarray, cutoff: float, fs: float = FS, order: int = 3) -> np.ndarray:
+    """Zero-phase Butterworth low-pass filter applied along axis 0.
+
+    Args:
+        data: 1-D or 2-D array
+        cutoff: cutoff frequency in Hz
+        fs: sampling rate in Hz
+        order: filter order
+
+    Returns:
+        Filtered array, same shape as input
+    """
+    b, a = sp_signal.butter(order, cutoff / (fs / 2.0), btype="low")
+    if data.ndim == 1:
+        return sp_signal.filtfilt(b, a, data)
+    return np.column_stack(
+        [sp_signal.filtfilt(b, a, data[:, i]) for i in range(data.shape[1])]
+    )
+
+
+def _median_filt(data: np.ndarray, k: int = 3) -> np.ndarray:
+    """Median filter applied along axis 0.
+
+    Args:
+        data: 1-D or 2-D array
+        k: kernel size (must be odd)
+
+    Returns:
+        Filtered array, same shape as input
+    """
+    if data.ndim == 1:
+        return sp_signal.medfilt(data, kernel_size=k)
+    return np.column_stack(
+        [sp_signal.medfilt(data[:, i], kernel_size=k) for i in range(data.shape[1])]
+    )
+
+
+def _burg_ar(x: np.ndarray, order: int = AR_ORDER) -> np.ndarray:
+    """Burg method autoregressive coefficients.
+
+    Implements the standard Burg recursion with Levinson-Durbin update.
+    Mean-centres the signal before fitting.
+
+    Args:
+        x: 1-D signal array
+        order: AR model order
+
+    Returns:
+        Array of `order` AR coefficients [a1, a2, ..., ap]
+    """
+    x = np.asarray(x, dtype=np.float64)
+    x = x - x.mean()
+    N = len(x)
+    ef = x.copy()
+    eb = x.copy()
+    a = np.zeros(order)
+
+    for m in range(1, order + 1):
+        f = ef[m:].copy()
+        b = eb[m - 1: N - 1].copy()
+
+        denom = np.dot(f, f) + np.dot(b, b) + 1e-12
+        km = -2.0 * np.dot(f, b) / denom
+
+        # Levinson-Durbin update of AR polynomial
+        a_prev = a[:m - 1].copy()
+        for j in range(m - 1):
+            a[j] = a_prev[j] + km * a_prev[m - 2 - j]
+        a[m - 1] = km
+
+        # Update forward/backward prediction errors
+        ef[m:] = f + km * b
+        eb[m - 1: N - 1] = b + km * f
+
+    return a
+
+
+def _entropy(x: np.ndarray) -> float:
+    """Normalised signal entropy via absolute-value probability distribution.
+
+    Args:
+        x: 1-D array
+
+    Returns:
+        Entropy value (>= 0)
+    """
+    total = np.abs(x).sum()
+    if total < 1e-12:
+        return 0.0
+    p = np.abs(x) / total
+    p = p[p > 0]
+    return float(-np.sum(p * np.log(p)))
+
+
+def _bands_energy(fft_mag: np.ndarray) -> np.ndarray:
+    """Energy in each of the 14 UCI HAR frequency bands (1-indexed, inclusive).
+
+    Args:
+        fft_mag: FFT magnitude array, must contain at least 64 values
+
+    Returns:
+        Array of 14 energy values
+    """
+    m = fft_mag[:64]
+    return np.array([float(np.sum(m[s - 1: e] ** 2)) for s, e in BANDS])
+
+
+def _safe_corr(a: np.ndarray, b: np.ndarray) -> float:
+    """Pearson correlation, returns 0.0 if either signal is constant.
+
+    Args:
+        a: first 1-D array
+        b: second 1-D array
+
+    Returns:
+        Correlation coefficient in [-1, 1]
+    """
+    if a.std() < 1e-10 or b.std() < 1e-10:
+        return 0.0
+    r = np.corrcoef(a, b)[0, 1]
+    return 0.0 if not np.isfinite(r) else float(r)
+
+
+def _angle(u: np.ndarray, v: np.ndarray) -> float:
+    """Angle in radians between two 3-D vectors.
+
+    Args:
+        u: first vector, shape (3,)
+        v: second vector, shape (3,)
+
+    Returns:
+        Angle in radians, or 0.0 if either vector is zero
+    """
+    un, vn = np.linalg.norm(u), np.linalg.norm(v)
+    if un < 1e-10 or vn < 1e-10:
+        return 0.0
+    return float(np.arccos(np.clip(np.dot(u, v) / (un * vn), -1.0, 1.0)))
+
+
+# ── Feature extractors ────────────────────────────────────────────────────────
+
+def _t3ax(sig: np.ndarray) -> np.ndarray:
+    """40 time-domain features from a 3-axis signal (N, 3).
+
+    Order: mean×3, std×3, mad×3, max×3, min×3, sma,
+           energy×3, iqr×3, entropy×3, arCoeff×12, correlation×3
+    """
+    N = len(sig)
+    x, y, z = sig[:, 0], sig[:, 1], sig[:, 2]
+    out = []
+
+    out += [x.mean(), y.mean(), z.mean()]
+    out += [x.std(), y.std(), z.std()]
+    out += [
+        float(np.median(np.abs(x - np.median(x)))),
+        float(np.median(np.abs(y - np.median(y)))),
+        float(np.median(np.abs(z - np.median(z)))),
+    ]
+    out += [x.max(), y.max(), z.max()]
+    out += [x.min(), y.min(), z.min()]
+    out += [float((np.abs(x) + np.abs(y) + np.abs(z)).sum() / N)]   # sma
+    out += [float(np.sum(x ** 2) / N), float(np.sum(y ** 2) / N), float(np.sum(z ** 2) / N)]
+    out += [
+        float(np.percentile(x, 75) - np.percentile(x, 25)),
+        float(np.percentile(y, 75) - np.percentile(y, 25)),
+        float(np.percentile(z, 75) - np.percentile(z, 25)),
+    ]
+    out += [_entropy(x), _entropy(y), _entropy(z)]
+    out += _burg_ar(x).tolist()
+    out += _burg_ar(y).tolist()
+    out += _burg_ar(z).tolist()
+    out += [_safe_corr(x, y), _safe_corr(x, z), _safe_corr(y, z)]
+
+    return np.array(out, dtype=np.float64)   # 40 values
+
+
+def _tmag(sig: np.ndarray) -> np.ndarray:
+    """13 time-domain features from a 1-D magnitude signal.
+
+    Order: mean, std, mad, max, min, sma, energy, iqr, entropy, arCoeff×4
+    """
+    N = len(sig)
+    out = [
+        float(sig.mean()),
+        float(sig.std()),
+        float(np.median(np.abs(sig - np.median(sig)))),
+        float(sig.max()),
+        float(sig.min()),
+        float(np.abs(sig).sum() / N),            # sma (1-D)
+        float(np.sum(sig ** 2) / N),             # energy
+        float(np.percentile(sig, 75) - np.percentile(sig, 25)),
+        _entropy(sig),
+    ]
+    out += _burg_ar(sig).tolist()
+    return np.array(out, dtype=np.float64)   # 13 values
+
+
+def _f3ax(sig: np.ndarray) -> np.ndarray:
+    """79 frequency-domain features from a 3-axis signal (N, 3).
+
+    Order: mean×3, std×3, mad×3, max×3, min×3, sma,
+           energy×3, iqr×3, entropy×3,
+           maxInds×3, meanFreq×3,
+           (skewness, kurtosis)×3 interleaved,
+           bandsEnergy×14 per axis (×3 axes = 42)
+    """
+    x, y, z = sig[:, 0], sig[:, 1], sig[:, 2]
+
+    def _fft(s):
+        return np.abs(np.fft.rfft(s))[:64]
+
+    fx, fy, fz = _fft(x), _fft(y), _fft(z)
+    bins = np.arange(1, 65, dtype=np.float64)   # 1-indexed bin numbers
+
+    def _mfreq(fm):
+        t = fm.sum()
+        return float(np.dot(bins[:len(fm)], fm) / t) if t > 1e-12 else 0.0
+
+    def _maxinds(fm):
+        return float(np.argmax(fm) + 1)   # 1-indexed
+
+    out = []
+    out += [fx.mean(), fy.mean(), fz.mean()]
+    out += [fx.std(), fy.std(), fz.std()]
+    out += [
+        float(np.median(np.abs(fx - np.median(fx)))),
+        float(np.median(np.abs(fy - np.median(fy)))),
+        float(np.median(np.abs(fz - np.median(fz)))),
+    ]
+    out += [fx.max(), fy.max(), fz.max()]
+    out += [fx.min(), fy.min(), fz.min()]
+    n = len(fx)
+    out += [float((fx + fy + fz).sum() / n)]    # sma of FFT mags
+    out += [float(np.sum(fx ** 2) / n), float(np.sum(fy ** 2) / n), float(np.sum(fz ** 2) / n)]
+    out += [
+        float(np.percentile(fx, 75) - np.percentile(fx, 25)),
+        float(np.percentile(fy, 75) - np.percentile(fy, 25)),
+        float(np.percentile(fz, 75) - np.percentile(fz, 25)),
+    ]
+    out += [_entropy(fx), _entropy(fy), _entropy(fz)]
+    out += [_maxinds(fx), _maxinds(fy), _maxinds(fz)]
+    out += [_mfreq(fx), _mfreq(fy), _mfreq(fz)]
+    # skewness/kurtosis interleaved per axis (skX,kurX, skY,kurY, skZ,kurZ)
+    out += [float(skew(fx)), float(sp_kurtosis(fx))]
+    out += [float(skew(fy)), float(sp_kurtosis(fy))]
+    out += [float(skew(fz)), float(sp_kurtosis(fz))]
+    out += _bands_energy(fx).tolist()
+    out += _bands_energy(fy).tolist()
+    out += _bands_energy(fz).tolist()
+
+    return np.array(out, dtype=np.float64)   # 79 values
+
+
+def _fmag(sig: np.ndarray) -> np.ndarray:
+    """13 frequency-domain features from a 1-D magnitude signal.
+
+    Order: mean, std, mad, max, min, sma, energy, iqr, entropy,
+           maxInds, meanFreq, skewness, kurtosis
+    """
+    fm = np.abs(np.fft.rfft(sig))[:64]
+    n = len(fm)
+    bins = np.arange(1, n + 1, dtype=np.float64)
+    total = fm.sum()
+    out = [
+        float(fm.mean()),
+        float(fm.std()),
+        float(np.median(np.abs(fm - np.median(fm)))),
+        float(fm.max()),
+        float(fm.min()),
+        float(np.abs(fm).sum() / n),
+        float(np.sum(fm ** 2) / n),
+        float(np.percentile(fm, 75) - np.percentile(fm, 25)),
+        _entropy(fm),
+        float(np.argmax(fm) + 1),                                        # maxInds (1-indexed)
+        float(np.dot(bins, fm) / total) if total > 1e-12 else 0.0,      # meanFreq
+        float(skew(fm)),
+        float(sp_kurtosis(fm)),
+    ]
+    return np.array(out, dtype=np.float64)   # 13 values
+
+
+def _window_features(
+    body_acc: np.ndarray,
+    grav_acc: np.ndarray,
+    body_jerk: np.ndarray,
+    gyro: np.ndarray,
+    gyro_jerk: np.ndarray,
+) -> np.ndarray:
+    """Extract all 561 features from one pre-processed window.
+
+    Args:
+        body_acc:  body linear acceleration (128, 3) m/s²
+        grav_acc:  gravity component        (128, 3) m/s²
+        body_jerk: body jerk                (127, 3) m/s³
+        gyro:      angular velocity         (128, 3) rad/s
+        gyro_jerk: gyro jerk                (127, 3) rad/s²
+
+    Returns:
+        1-D array of 561 features
+    """
+    # Magnitudes
+    ba_mag = np.linalg.norm(body_acc, axis=1)
+    ga_mag = np.linalg.norm(grav_acc, axis=1)
+    bj_mag = np.linalg.norm(body_jerk, axis=1)
+    gy_mag = np.linalg.norm(gyro, axis=1)
+    gj_mag = np.linalg.norm(gyro_jerk, axis=1)
+
+    parts = []
+
+    # Time 3-axis (5 × 40 = 200)
+    for sig in [body_acc, grav_acc, body_jerk, gyro, gyro_jerk]:
+        parts.append(_t3ax(sig))
+
+    # Time magnitudes (5 × 13 = 65)
+    for mag in [ba_mag, ga_mag, bj_mag, gy_mag, gj_mag]:
+        parts.append(_tmag(mag))
+
+    # Freq 3-axis (3 × 79 = 237)
+    for sig in [body_acc, body_jerk, gyro]:
+        parts.append(_f3ax(sig))
+
+    # Freq magnitudes (4 × 13 = 52)
+    for mag in [ba_mag, bj_mag, gy_mag, gj_mag]:
+        parts.append(_fmag(mag))
+
+    # Angle features (7)
+    ba_mean = body_acc.mean(axis=0)
+    ga_mean = grav_acc.mean(axis=0)
+    bj_mean = body_jerk.mean(axis=0)
+    gy_mean = gyro.mean(axis=0)
+    gj_mean = gyro_jerk.mean(axis=0)
+
+    parts.append(np.array([
+        _angle(ba_mean, ga_mean),
+        _angle(bj_mean, ga_mean),
+        _angle(gy_mean, ga_mean),
+        _angle(gj_mean, ga_mean),
+        _angle(np.array([1.0, 0.0, 0.0]), ga_mean),
+        _angle(np.array([0.0, 1.0, 0.0]), ga_mean),
+        _angle(np.array([0.0, 0.0, 1.0]), ga_mean),
+    ]))
+
+    result = np.concatenate(parts)
+    assert result.shape == (561,), f"Feature count error: got {result.shape[0]}, expected 561"
+    return result
+
+
+# ── Public API ────────────────────────────────────────────────────────────────
+
+def process_phyphox_files(
+    acc_file,
+    gyro_file,
+) -> tuple:
+    """Convert Phyphox CSV exports to (n_windows, 561) feature array.
+
+    Pipeline:
+      1. Parse + validate both CSVs
+      2. Interpolate onto common 50 Hz grid
+      3. Segment: 128-sample windows, 64-sample hop (50% overlap)
+      4. Per window: median filter → 20 Hz Butterworth → gravity separation
+         at 0.3 Hz → jerk → magnitudes → 561 features
+
+    Args:
+        acc_file: file-like object — Phyphox Accelerometer CSV
+                  (columns: Time (s), X (m/s^2), Y (m/s^2), Z (m/s^2))
+        gyro_file: file-like object — Phyphox Gyroscope CSV
+                   (columns: Time (s), X (rad/s), Y (rad/s), Z (rad/s))
+
+    Returns:
+        Tuple of:
+          np.ndarray shape (n_windows, 561) �� raw (un-normalised) features
+          list[str]                          — warning messages
+
+    Raises:
+        ValueError: invalid format, wrong columns, or < 3 s of data
+    """
+    warnings: list = []
+
+    acc_df = _parse_csv(acc_file, ACC_COLS)
+    gyro_df = _parse_csv(gyro_file, GYRO_COLS)
+
+    acc_t = acc_df["Time (s)"].values
+    acc_xyz = acc_df[["X (m/s^2)", "Y (m/s^2)", "Z (m/s^2)"]].values
+    gyro_t = gyro_df["Time (s)"].values
+    gyro_xyz = gyro_df[["X (rad/s)", "Y (rad/s)", "Z (rad/s)"]].values
+
+    # Common time window
+    t0 = max(acc_t[0], gyro_t[0])
+    t1 = min(acc_t[-1], gyro_t[-1])
+    duration = t1 - t0
+
+    if duration < 3.0:
+        raise ValueError(
+            f"Recording is {duration:.2f} s — minimum 3 seconds required. "
+            "Hold the phone still or walk for at least 3 seconds before exporting."
+        )
+
+    t_grid = np.arange(t0, t1, 1.0 / FS)
+    am = (acc_t >= t0) & (acc_t <= t1)
+    gm = (gyro_t >= t0) & (gyro_t <= t1)
+
+    acc_50 = np.column_stack(
+        [np.interp(t_grid, acc_t[am], acc_xyz[am, i]) for i in range(3)]
+    )
+    gyro_50 = np.column_stack(
+        [np.interp(t_grid, gyro_t[gm], gyro_xyz[gm, i]) for i in range(3)]
+    )
+
+    n = min(len(acc_50), len(gyro_50))
+    acc_50, gyro_50 = acc_50[:n], gyro_50[:n]
+
+    n_windows = max(0, (n - WINDOW) // STEP + 1)
+    if n_windows == 0:
+        raise ValueError(
+            f"Only {n} samples ({n / FS:.1f} s) after alignment — "
+            f"need at least {WINDOW} samples ({WINDOW / FS:.1f} s)."
+        )
+
+    if duration > 60:
+        warnings.append(f"Long recording ({duration:.0f} s) — {n_windows} windows extracted.")
+
+    all_features = []
+    dt = 1.0 / FS
+
+    for start in range(0, n - WINDOW + 1, STEP):
+        end = start + WINDOW
+        aw = acc_50[start:end]    # (128, 3)
+        gw = gyro_50[start:end]   # (128, 3)
+
+        # 1. Noise: median filter then 3rd-order Butterworth LP at 20 Hz
+        aw = _butter_lp(_median_filt(aw), cutoff=20.0)
+        gw = _butter_lp(_median_filt(gw), cutoff=20.0)
+
+        # 2. Gravity separation: LP at 0.3 Hz
+        grav = _butter_lp(aw, cutoff=0.3)
+        body = aw - grav
+
+        # 3. Jerk: finite difference → (127, 3)
+        body_jerk = np.diff(body, axis=0) / dt
+        gyro_jerk = np.diff(gw, axis=0) / dt
+
+        all_features.append(_window_features(body, grav, body_jerk, gw, gyro_jerk))
+
+    return np.array(all_features), warnings

src/streamlit_app.py

@@ -7,6 +7,7 @@ import pandas as pd
 _SRC_DIR = os.path.dirname(os.path.abspath(__file__))
 _REPO_ROOT = os.path.dirname(_SRC_DIR)
 _SAMPLES_PATH = os.path.join(_REPO_ROOT, "data", "samples.csv")
+_NORM_PATH    = os.path.join(_REPO_ROOT, "data", "norm_params.json")
 
 # ── Constants ──────────────────────────────────────────────────────────────
 
@@ -193,36 +194,8 @@ with tab1:
     except FileNotFoundError:
         st.error("Sample data file not found. Add `data/samples.csv` to the repo.")
 
-# ── Tab 2: Phyphox upload (placeholder) ─────────────────────────────────────
+# ── Tab 2: Phyphox upload ─────────────────────────────────────────────────────
 
 with tab2:
-    st.subheader("Upload Phyphox sensor recording")
-    st.markdown("""
-    **How to record your own data:**
-    1. Install [Phyphox](https://phyphox.org/) on your phone
-    2. Open the **Acceleration (without g)** and **Gyroscope** experiments
-    3. Record at least 3 seconds of a single activity
-    4. Export as CSV and upload below
-    """)
-
-    uploaded_file = st.file_uploader(
-        "Upload Phyphox CSV export",
-        type=["csv"],
-        help="Export from Phyphox as CSV — must contain accelerometer and gyroscope columns"
-    )
-
-    if uploaded_file is not None:
-        st.info(
-            "Phyphox pipeline coming soon. "
-            "Feature extraction from raw sensor readings "
-            "(filtering → jerk → FFT → 561 features) is under development."
-        )
-        try:
-            preview = pd.read_csv(uploaded_file)
-            st.markdown("**File preview:**")
-            st.dataframe(preview.head(10))
-            st.caption(
-                f"{len(preview)} rows · {len(preview.columns)} columns detected"
-            )
-        except Exception as e:
-            st.error(f"Could not read file: {e}")
+    from phyphox_app_block import render_phyphox_tab
+    render_phyphox_tab(ffn_model, ffn_status, cnn_model, cnn_status, _NORM_PATH)