Teaching Computers to Learn•Interactive notebook lesson•Free
model analysis
No account is required. Learn the material, try the examples, and mark it complete locally when you are ready to move on.
Codepython
"""
IMDB Sentiment Model Analysis Script
This script:
1. Loads the trained sentiment model
2. Loads the IMDB dataset
3. Applies the same preprocessing
4. Generates predictions
5. Evaluates performance
6. Analyzes misclassified reviews
"""
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.metrics import confusion_matrix, classification_report
from tensorflow.keras.preprocessing.sequence import pad_sequences
# -------------------------------
# 1. Load Model
# -------------------------------
print("Loading model...")
model = tf.keras.models.load_model(
"./models/imdb_sentiment_model.keras",
compile=False,
safe_mode=False
)
model.summary()
Output
2026-03-16 02:40:38.138013: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2026-03-16 02:40:38.160818: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2026-03-16 02:40:38.160839: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2026-03-16 02:40:38.161427: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2026-03-16 02:40:38.165421: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2026-03-16 02:40:38.589286: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
2026-03-16 02:40:39.526859: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2026-03-16 02:40:39.548890: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2026-03-16 02:40:39.551115: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2026-03-16 02:40:39.554600: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2026-03-16 02:40:39.556773: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2026-03-16 02:40:39.558925: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2026-03-16 02:40:39.638588: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2026-03-16 02:40:39.639484: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2026-03-16 02:40:39.640241: I external/local_xla/xla/stream_executor/cuda/cuda_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2026-03-16 02:40:39.641012: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1929] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10105 MB memory: -> device: 0, name: NVIDIA GeForce RTX 3060, pci bus id: 0000:01:00.0, compute capability: 8.6
# -------------------------------
# 8. Decode Reviews
# -------------------------------
word_index = tf.keras.datasets.imdb.get_word_index()
reverse_word_index = {value + 3: key for key, value in word_index.items()}
reverse_word_index[0] = "<PAD>"
reverse_word_index[1] = "<START>"
reverse_word_index[2] = "<UNK>"
reverse_word_index[3] = "<UNUSED>"
def decode_review(text):
return " ".join([reverse_word_index.get(i, "?") for i in text])
# -------------------------------
# 9. Misclassified Reviews
# -------------------------------
misclassified = np.where(pred_labels != test_labels)[0]
print("\nTotal misclassified:", len(misclassified))
print("\nShowing 5 misclassified reviews:\n")
for i in misclassified[:5]:
print("Actual:", test_labels[i])
print("Predicted:", pred_labels[i])
print("Confidence:", predictions[i][0])
print("\nReview text:\n")
print(decode_review(test_data[i]))
print("\n" + "-"*80 + "\n")
Output
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb_word_index.json
1641221/1641221 [==============================] - 0s 0us/step
Total misclassified: 3500
Showing 5 misclassified reviews:
Actual: 1
Predicted: 0
Confidence: 0.40020066
Review text:
<START> i'm absolutely disgusted this movie isn't being sold all who love this movie should email disney and increase the demand for it they'd eventually have to sell it then i'd buy copies for everybody i know everything and everybody in this movie did a good job and i haven't figured out why disney hasn't put this movie on dvd or on vhs in rental stores at least i haven't seen any copies this is a wicked good movie and should be seen by all the kids in the new generation don't get to see it and i think they should it should at least be put back on the channel this movie doesn't deserve a cheap <UNK> it deserves the real thing i'm them now this movie will be on dvd <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD>
--------------------------------------------------------------------------------
Actual: 0
Predicted: 1
Confidence: 0.80630004
Review text:
<START> hollywood had a long love affair with bogus <UNK> nights tales but few of these products have stood the test of time the most memorable were the jon hall maria <UNK> films which have long since become camp this one is filled with dubbed songs <UNK> <UNK> and slapstick it's a truly crop of corn and pretty near <UNK> today it was nominated for its imaginative special effects which are almost <UNK> in this day and age <UNK> mainly of trick photography the only outstanding positive feature which survives is its beautiful color and clarity sad to say of the many films made in this genre few of them come up to alexander <UNK> original thief of <UNK> almost any other <UNK> nights film is superior to this one though it's a loser <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD>
--------------------------------------------------------------------------------
Actual: 0
Predicted: 1
Confidence: 0.6713709
Review text:
<START> if you have never read the classic science fiction novel this mini series is based on it may actually be good unfortunately if you are a fan of the book you probably won't be able to watch more than the first hour or two all of the political intrigue has been taken out of the film the most important scenes from the book have been taken out characters motivations have been changed completely and words from the wrong characters mouths where in the novel paul was a teen age boy with incredible political skill and a great understanding of the way the world worked in this film he is hot headed and and frustrated avoid this movie at all costs <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD>
--------------------------------------------------------------------------------
Actual: 0
Predicted: 1
Confidence: 0.5733637
Review text:
<START> oh how awfully this movie is i don't know if it is a horror film or a drama cause the story and the both genres are not established very well the story is not moving it is slow boring and sleepy from the beginning to end this movie really <UNK> me but i really liked the camera work it is authentic fresh and clear the acting is great too the little boy was the great performer in this movie but it hasn't made me to jump from my seat but this movie makes me grab a <UNK> lay on the bed and sleep until the credits roll br br boring not worth watching i tell you this movie sucked br br 1 10 <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD>
--------------------------------------------------------------------------------
Actual: 1
Predicted: 0
Confidence: 0.48462266
Review text:
<START> alice is the kind of movie they made in the 30's and 40's never attempts to be an event just wants to entertain and it does i was surprised by <UNK> sutherland in a role that could be a cliche he made it real the plot does make <UNK> to alice in wonderland a guy dressed in white does go through a hole and <UNK> does fall down one like alice the plot does twist and turn but with a <UNK> you don't see in small movies i loved the direction sutherland just a very fast paced and interesting movie <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD> <PAD>
--------------------------------------------------------------------------------
Codepython
Codepython
Codepython
Codepython
Codepython
Codepython
Codepython
Lesson resources
Supporting code and files from this part of the curriculum.
