Changed all files in dev_code to have correct file paths

BU-Spark · Jun 28, 2024 · 1ca1598 · 1ca1598
1 parent ef761eb
commit 1ca1598
Show file tree

Hide file tree

Showing 37 changed files with 22 additions and 276 deletions.
diff --git a/data/db_filenames.csv b/data/db_filenames.csv
diff --git a/dev_code/old notebook with bad code.ipynb → dev_code/kmeans_pca_testing.ipynb b/dev_code/old notebook with bad code.ipynb → dev_code/kmeans_pca_testing.ipynb
@@ -224,7 +224,7 @@
     "from sklearn.cluster import KMeans\n",
     "from kmodes.kprototypes import KPrototypes\n",
     "\n",
-    "k_df = pd.read_csv(\"all data/citizen/maharashtra.csv\")\n",
+    "k_df = pd.read_csv(\"../data/citizen_states_cleaned/maharashtra.csv\")\n",
     "k_df = k_df[k_df[\"Species_name\"] == \"Peepal-Ficus religiosa\"]\n",
     "\n",
     "species = {}\n",
@@ -466,7 +466,7 @@
     "from sklearn.preprocessing import OneHotEncoder\n",
     "import numpy as np\n",
     "\n",
-    "k_df = pd.read_csv(\"all data/citizen/maharashtra.csv\")\n",
+    "k_df = pd.read_csv(\"../data/citizen_states_cleaned/maharashtra.csv\")\n",
     "k_df = k_df[k_df[\"Species_name\"] == \"Peepal-Ficus religiosa\"]\n",
     "\n",
     "k_df = k_df.drop([\"Date_of_observation\", \"Observation_ID\", \"User_id\", \"User_Tree_id\", \"Lat\", \"Long\"], axis=1)\n",
@@ -515,16 +515,6 @@
     "plt.ylabel('Principal Component 2')\n",
     "plt.show()"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f7cf1ba4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# "
-   ]
   }
  ],
  "metadata": {
@@ -543,7 +533,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,

diff --git a/dev_code/mean transition times from repeat observations.ipynb b/dev_code/mean transition times from repeat observations.ipynb
@@ -81,7 +81,7 @@
    "outputs": [],
    "source": [
     "def plot_probs(species_id, attr, year):\n",
-    "    state_df = pd.read_csv('all data/citizen/kerala.csv')\n",
+    "    state_df = pd.read_csv('../data/citizen_states_cleaned/kerala.csv')\n",
     "    transition_data = get_transition_data(state_df, species_id, attr, year)\n",
     "    transition_probs = transition_data / np.sum(transition_data)\n",
     "    pcts = get_percent_data(state_df, species_id, attr, year)\n",
@@ -186,7 +186,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,

diff --git a/dev_code/mean_transition_times_dev.ipynb b/dev_code/mean_transition_times_dev.ipynb
@@ -153,7 +153,7 @@
    "outputs": [],
    "source": [
     "def plot_score_and_pcts(species_id, attr, L=5, M=3, w_1=1, w_2=1, w_3=1, size_term=False):\n",
-    "    state_df = pd.read_csv('all data/citizen/kerala.csv')\n",
+    "    state_df = pd.read_csv('../data/citizen_state_names/kerala.csv')\n",
     "    pcts = []\n",
     "    for year in range(2018, 2024):\n",
     "        pcts += get_percent_of_positive_observations_for_each_week(state_df, year, species_id, attr)\n",
@@ -209,7 +209,7 @@
    "outputs": [],
    "source": [
     "def plot_score_for_one_year(year, species_id, attr, L=5, M=3, w_1=1, w_2=1):\n",
-    "    state_df = pd.read_csv('all data/citizen/kerala.csv')\n",
+    "    state_df = pd.read_csv('../data/citizen_state_names/kerala.csv')\n",
     "    pcts = []\n",
     "    for y in range(2018, 2024):\n",
     "        pcts += get_percent_of_positive_observations_for_each_week(state_df, y, species_id, attr)\n",
@@ -250,7 +250,7 @@
    "outputs": [],
    "source": [
     "def plot_stagnations(species_id, attr, L=5, M=3, w_1=1, w_2=1, w_3=1, size_term=False):\n",
-    "    state_df = pd.read_csv('all data/citizen/kerala.csv')\n",
+    "    state_df = pd.read_csv('../data/citizen_state_names/kerala.csv')\n",
     "    pcts = []\n",
     "    if size_term:\n",
     "        scores, spikes, stagns, sizes = get_scores(state_df, species_id, attr, L=L, M=M, w_1=w_1, w_2=w_2, w_3=w_3, size_term=size_term)\n",
@@ -300,7 +300,7 @@
     "    #     plt.title(f\"Average transition time for Mango (all species) {attr} in Kerala, {year}, L={L}, M={M}, w_1={w_1}, w_2={w_2}\")\n",
     "\n",
     "def plot_spikes(species_id, attr, L=5, M=3, w_1=1, w_2=1, w_3=1, size_term=False):\n",
-    "    state_df = pd.read_csv('all data/citizen/kerala.csv')\n",
+    "    state_df = pd.read_csv('../data/citizen_state_names/kerala.csv')\n",
     "    pcts = []\n",
     "    for year in range(2018, 2024):\n",
     "        pcts += get_percent_of_positive_observations_for_each_week(state_df, year, species_id, attr)\n",
@@ -3247,7 +3247,7 @@
     }
    ],
    "source": [
-    "state_df = pd.read_csv('all data/citizen/kerala.csv')\n",
+    "state_df = pd.read_csv('../data/citizen_state_names/kerala.csv')\n",
     "top_20_species = state_df['Species_id'].value_counts().index.tolist()[:20]\n",
     "for species_id in top_20_species:\n",
     "    for w_1 in [0.5]:\n",
@@ -3319,7 +3319,7 @@
     "    return list(scores), list(spikes), list(stagns)\n",
     "\n",
     "def plot_score_and_pcts(species_id, attr, L=5, M_short=3, M_long=15, w_1=1, w_2=1, w_3=1, size_term=False):\n",
-    "    state_df = pd.read_csv('all data/citizen/kerala.csv')\n",
+    "    state_df = pd.read_csv('../data/citizen_state_names/kerala.csv')\n",
     "    pcts = []\n",
     "    for year in range(2018, 2024):\n",
     "        pcts += get_percent_of_positive_observations_for_each_week(state_df, year, species_id, attr)\n",
@@ -3367,7 +3367,7 @@
     "        plt.title(f\"Average transition time for Mango (all species) {attr} in Kerala, {year}, L={L}, M_short={M_short}, M_long={M_long}, w_1={w_1}, w_2={w_2}, w_3={w_3}\")\n",
     "\n",
     "def plot_spikes(species_id, attr, L=5, M_short=3, M_long=15, w_1=1, w_2=1, w_3=1, size_term=False):\n",
-    "    state_df = pd.read_csv('all data/citizen/kerala.csv')\n",
+    "    state_df = pd.read_csv('../data/citizen_state_names/kerala.csv')\n",
     "    pcts = []\n",
     "    for year in range(2018, 2024):\n",
     "        pcts += get_percent_of_positive_observations_for_each_week(state_df, year, species_id, attr)\n",
@@ -3402,7 +3402,7 @@
     "    plt.show()\n",
     "\n",
     "def plot_stagnations(species_id, attr, L=5, M_short=3, M_long=15, w_1=1, w_2=1, w_3=1, size_term=False):\n",
-    "    state_df = pd.read_csv('all data/citizen/kerala.csv')\n",
+    "    state_df = pd.read_csv('../data/citizen_state_names/kerala.csv')\n",
     "    pcts = []\n",
     "    if size_term:\n",
     "        scores, spikes, stagns, sizes = get_scores(state_df, species_id, attr, L=L, M_short=M_short, M_long=M_long, w_1=w_1, w_2=w_2, w_3=w_3, size_term=size_term)\n",
@@ -4613,7 +4613,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,