Upload New File

Base_Frequency.py

+import numpy as np
+import scipy.io.wavfile as wavfile
+
+# Define the bases and frequencies for different moods
+happy_base = 440
+happy_freqs = np.array([0.5, 1, 1.5, 2, 2.5, 3])
+sad_base = 220
+sad_freqs = np.array([1, 1.25, 1.5, 1.75, 2, 2.25])
+
+def classify_mood(base, freqs, song):
+    # Compute the FFT of the song
+    fft = np.fft.fft(song)
+    # Compute the magnitudes of the FFT
+    mag = np.abs(fft)
+    # Find the index of the peak frequency
+    peak_idx = np.argmax(mag)
+    # Compute the frequency corresponding to the peak index
+    peak_freq = peak_idx / len(song)
+    # Compute the difference between the peak frequency and the expected frequencies
+    diffs = np.abs(peak_freq - freqs)
+    # Find the index of the closest expected frequency
+    closest_idx = np.argmin(diffs)
+    # Compute the difference between the base and the peak frequency
+    base_diff = np.abs(base - peak_freq)
+    # If the base difference is less than 0.1, classify as the expected mood, otherwise classify as "unknown"
+    if base_diff < 0.1:
+        return "happy" if base == happy_base else "sad"
+    else:
+        return "unknown"
+
+# Load the song from a .wav file
+fs, song = wavfile.read("Pop2.wav")
+song = song / 32767.0  # Normalize the song to the range [-1, 1]
+
+# Example usage:
+mood = classify_mood(happy_base, happy_freqs, song)
+print(mood)  # Output: "happy"