All sklearn modules used in Udacity "Intro to machine learning" lessons. Refer to [here](https://classroom.udacity.com/courses/ud120)

mods_in_udacity_intro_to_ml_lessons.json

{
  "train_test_split": {
    "raw": [
      "outliers/outlier_removal_regression.py:23:from sklearn.cross_validation import train_test_split",
      "regression/finance_regression.py:30:from sklearn.cross_validation import train_test_split",
      "pca/eigenfaces.py:26:from sklearn.cross_validation import train_test_split",
      "final_project/poi_id.py.bak:52:from sklearn.cross_validation import train_test_split",
      "final_project/poi_id.py:67:    from sklearn.cross_validation import train_test_split",
      "validation/validate_poi.py:32:from sklearn.model_selection import train_test_split",
      "evaluation/validate_poi.py:32:from sklearn.model_selection import train_test_split",
      "evaluation/evaluate_poi_identifier.py:31:from sklearn.model_selection import train_test_split"
    ]
  },
  "LinearRegression": {
    "raw": [
      "outliers/outlier_removal_regression.py:28:from sklearn.linear_model import LinearRegression",
      "regression/finance_regression.py:41:from sklearn.linear_model import LinearRegression"
    ]
  },
  "TfidfVectorizer": {
    "raw": [
      "text_learning/vectorize_text.py:88:from sklearn.feature_extraction.text import TfidfVectorizer",
      "feature_selection/find_signature.py:23:from sklearn.feature_extraction.text import TfidfVectorizer",
      "tools/email_preprocess.py:8:from sklearn.feature_extraction.text import TfidfVectorizer"
    ]
  },
  "stop_words": {
    "raw": [
      "text_learning/vectorize_text.py:89:from sklearn.feature_extraction import stop_words"
    ]
  },
  "RandomForestClassifier": {
    "raw": [
      "choose_your_own/your_algorithm.py:33:from sklearn.ensemble import RandomForestClassifier"
    ]
  },
  "AdaBoostClassifier": {
    "raw": [
      "choose_your_own/your_algorithm.py:34:from sklearn.ensemble import AdaBoostClassifier"
    ]
  },
  "KNeighborsClassifier": {
    "raw": [
      "choose_your_own/your_algorithm.py:35:from sklearn.neighbors import KNeighborsClassifier"
    ]
  },
  "cross_validation": {
    "raw": [
      "feature_selection/find_signature.py:20:from sklearn import cross_validation",
      "tools/email_preprocess.py:7:from sklearn import cross_validation"
    ]
  },
  "DecisionTreeClassifier": {
    "raw": [
      "feature_selection/find_signature.py:54:from sklearn.tree import DecisionTreeClassifier",
      "decision_tree/dt_author_id.py:27:from sklearn.tree import DecisionTreeClassifier",
      "validation/validate_poi.py:31:from sklearn.tree import DecisionTreeClassifier",
      "evaluation/validate_poi.py:31:from sklearn.tree import DecisionTreeClassifier",
      "evaluation/evaluate_poi_identifier.py:30:from sklearn.tree import DecisionTreeClassifier"
    ]
  },
  "KMeans": {
    "raw": [
      "k_means/k_means_cluster.py:109:from sklearn.cluster import KMeans"
    ]
  },
  "SVC": {
    "raw": [
      "svm/svm_author_id.py:28:from sklearn.svm import SVC",
      "pca/eigenfaces.py:32:from sklearn.svm import SVC"
    ]
  },
  "fetch_lfw_people": {
    "raw": [
      "pca/eigenfaces.py:27:from sklearn.datasets import fetch_lfw_people"
    ]
  },
  "GridSearchCV": {
    "raw": [
      "pca/eigenfaces.py:28:from sklearn.grid_search import GridSearchCV"
    ]
  },
  "classification_report": {
    "raw": [
      "pca/eigenfaces.py:29:from sklearn.metrics import classification_report"
    ]
  },
  "confusion_matrix": {
    "raw": [
      "pca/eigenfaces.py:30:from sklearn.metrics import confusion_matrix"
    ]
  },
  "RandomizedPCA": {
    "raw": [
      "pca/eigenfaces.py:31:from sklearn.decomposition import RandomizedPCA"
    ]
  },
  "GaussianNB": {
    "raw": [
      "final_project/poi_id.py.bak:41:from sklearn.naive_bayes import GaussianNB",
      "final_project/poi_id.py:56:    from sklearn.naive_bayes import GaussianNB",
      "naive_bayes/nb_author_id.py:29:from sklearn.naive_bayes import GaussianNB"
    ]
  },
  "StratifiedShuffleSplit": {
    "raw": [
      "final_project/tester.py:15:from sklearn.cross_validation import StratifiedShuffleSplit"
    ]
  },
  "VarianceThreshold": {
    "raw": [
      "final_project/poi_id.py:6:from sklearn.feature_selection import VarianceThreshold"
    ]
  },
  "PCA": {
    "raw": [
      "final_project/poi_id.py:7:from sklearn.decomposition import PCA"
    ]
  },
  "SelectPercentile, f_classif": {
    "raw": [
      "tools/email_preprocess.py:9:from sklearn.feature_selection import SelectPercentile, f_classif"
    ]
  },
  "sklearn": {
    "raw": [
      "tools/startup.py:24:    import sklearn"
    ]
  },
  "metrics": {
    "raw": [
      "evaluation/evaluate_poi_identifier.py:32:from sklearn import metrics"
    ]
  }
}

thing_generator.py

## Used this script to generate the file
## Use this script at `ud120-projects`

# 'meh' file contains output of `grep -nr "sklearn" --exclude-dir="maildir" --exclude="*.txt" --exclude="*.pkl"`
with open('meh') as f:
    c = f.read()

lines = c.split("\n")
target_str = "import "

occurrences = []
_mods = []
mods = {}
for line in lines:
    splits = line.split(":")
    candidate = splits[-1]
    if 'import' not in candidate:
        continue

    pos = candidate.find(target_str)
    pos1 = pos + len(target_str)
    mod = candidate[pos1:]
    
    if mod not in _mods:
        mods[mod] = {
            'raw': [line]
        }
        _mods.append(mod)
    else:
        mods[mod]['raw'].append(line)

print(mods)

# unique_mods = list(set(mods))
# from pprint import pprint
# pprint(unique_mods)

import json

with open('mods_in_lesson', 'w') as f:
    json.dump(mods, f, indent=2)