MaxHilsdorf

Häxor are a rare species fruktade by the common folk for their use of mäktiga magic. However, häxorna are often missförstådda.

häxor: Witches
fruktade: feared
mäktiga: powerful/mighty
missförstådda: misunderstood

MaxHilsdorf

MaxHilsdorf

from tensorflow import keras
from keras import Sequential
from keras.layers import Conv2D, MaxPool2D, BatchNormalization, Flatten, Dense, Dropout, GRU, Reshape

model = Sequential(name="gtzan_crnn")

# Convolutional Block 1
model.add(Conv2D(filters=16, kernel_size=(3,3), input_shape=X_train.shape[1:])) # X_train holds the processed training spectrograms
model.add(MaxPool2D(pool_size=(2,2)))
model.add(BatchNormalization())

MaxHilsdorf

{
    "project_folders": {
        "base_folder": "my_path/gtzan/",
        "raw_mp3_folder": "raw_mp3s/"
    },

    "build_dataset_params":{

        "audio_slicing_params":{
            "sliced_mp3_folder": "processed_mp3s/",

MaxHilsdorf

def recommend(track_id, ref_df, sp, n_recs = 5):
    
    # Crawl valence and arousal of given track from spotify api
    track_features = sp.track_audio_features(track_id)
    track_moodvec = np.array([track_features.valence, track_features.energy])
    
    # Compute distances to all reference tracks
    ref_df["distances"] = ref_df["mood_vec"].apply(lambda x: norm(track_moodvec-np.array(x)))
    # Sort distances from lowest to highest
    ref_df_sorted = ref_df.sort_values(by = "distances", ascending = True)

MaxHilsdorf

#################
## PREPARATION ##
#################

# Import modules
import sys
# If your authentification script is not in the project directory
# append its folder to sys.path
sys.path.append("../spotify_api_web_app")
import authorization

MaxHilsdorf

ax.text(quant_5-.1, 0.17, "5th", size = 10, alpha = 0.8)
ax.text(quant_25-.13, 0.27, "25th", size = 11, alpha = 0.85)
ax.text(quant_50-.13, 0.37, "50th", size = 12, alpha = 1)
ax.text(quant_75-.13, 0.47, "75th", size = 11, alpha = 0.85)
ax.text(quant_95-.25, 0.57, "95th Percentile", size = 10, alpha =.8)

MaxHilsdorf

# Calculate percentiles
quant_5, quant_25, quant_50, quant_75, quant_95 = avocado.quantile(0.05), avocado.quantile(0.25), avocado.quantile(0.5), avocado.quantile(0.75), avocado.quantile(0.95)

# [quantile, opacity, length]
quants = [[quant_5, 0.6, 0.16], [quant_25, 0.8, 0.26], [quant_50, 1, 0.36],  [quant_75, 0.8, 0.46], [quant_95, 0.6, 0.56]]

# Plot the lines with a loop
for i in quants:
    ax.axvline(i[0], alpha = i[1], ymax = i[2], linestyle = ":")

MaxHilsdorf

fig, ax = plt.subplots(figsize = (6,4))

# Plots #
    # Plot histogram
avocado.plot(kind = "hist", density = True, bins = 15) # change density to true, because KDE uses density
    # Plot KDE
avocado.plot(kind = "kde")

# X #
ax.set_xlabel("Average Price ($)")

MaxHilsdorf

fig, ax = plt.subplots(figsize = (6,4))

# Plots #
    # Plot histogram
avocado.plot(kind = "hist", density = True, bins = 15) # change density to true, because KDE uses density
    # Plot KDE
avocado.plot(kind = "kde")

# X #
ax.set_xlabel("Average Price ($)")